Creator · darkroomengineering
Last updated · Aug 24, 2026
handoff
End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "context window", "running out of context", "done for today" (save mode); "continue where we left off", "pick up where", "last session", "previous work", "resume" (resume mode).
Sandbox only
Install targets
Codex install prompt
Install the "handoff" agent skill from https://github.com/darkroomengineering/cc-settings/tree/main/skills/handoff. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "context window", "running out of context", "done for today" (save mode); "continue where we left off", "pick up where", "last session", "previous work", "resume" (resume mode). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {"event_id":"install_<unique-id>","skill_slug":"darkroomengineering-handoff","task":"Install handoff","agent":"codex","outcome":"success","install_used":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.Supply asset profile
Coding and developer agents
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
Scenario
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Agent fit
Claude Code + OpenAI Agents + CLI
Codex, Claude Code, Cursor, CLI, or custom agents.
Install
Ready
npx skills add darkroomengineering/cc-settings --skill handoff
Maintenance
fresh
Pushed today
Risk
Needs review
Dependency or permission surface needs review
GitHub quality
42
63/100 Quality · 72/100 Trust
Coverage tags
Review notes
Dependency or permission surface needs review · Permission surface may require sandboxing
Agent adoption scorecard
Trust, audit, and install readiness at a glance
These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.
Quality
PromisingUseful candidate, but compare it with alternatives before adopting.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
OpenAgentSkill Trust Score v5
Human review before install
Run only in a sandbox and compare close alternatives before using it for real work.
Stars
42 GitHub stars
Repo activity
42 stars, 3 forks
Maintenance
Pushed today
License
MIT
Install
npx skills add darkroomengineering/cc-settings --skill handoff
Install safety
standard package or runtime install path
Permission surface
secrets or environment access, shell or command execution
Agent outcomes
No agent outcome data yet
Docs
Strong README/SKILL.md context
Risk summary
Review before production
- Financial research output is not financial advice; require human review before any live investment decision.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
Install readiness
Install path available
- Install path is available
- Repository evidence is available
- License is declared
- No Agent Proven outcome evidence yet
Agent-readable metadata
Machine-readable decision data for this skill.
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
View technical data+
Agent-readable metadata
Machine-readable decision data for this skill.
Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.
Suited tasks
- Research agents workflows
- Claude Code teams
- builders willing to evaluate younger projects
- Search sources
Suited agents
Install decision
- Command
- npx skills add darkroomengineering/cc-settings --skill handoff
- Policy
- block
- Human review
- yes
Trust and risk
- Trust
- 64/100
- Audit
- 76/100
- Risk level
- Needs review
Outcome loop
- Endpoint
- /api/agent/outcome
- Event ID
- resolve
- Outcomes
- 5
Install command
npx skills add darkroomengineering/cc-settings --skill handoffDo not use when
- teams that need a vendor-supported SLA
- production agents without a repository review
- Low GitHub adoption signal
- No OpenAgentSkill engagement data yet
- High-risk permission hints: Shell or command execution, Secrets or environment access
Agent safety v2
36/100 · Avoid automatic install
This skill should not be selected by an agent without explicit human security review.
Do not auto-install. Inspect the source, dependencies, and permission surface first.
high
Shell or command execution
Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.
medium
Network access
Skill likely fetches remote pages, APIs, repositories, or external services.
medium
Filesystem access
Skill may read or write project files, documents, generated artifacts, or local workspace state.
high
Secrets or environment access
Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.
- High-risk permission hints: Shell or command execution, Secrets or environment access
- Dependency or permission surface needs review
Agent resolve plan
Let an agent verify fit before installing.
The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.
Open JSON
/api/agent/resolve?task=Use%20handoff%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20handoff%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/darkroomengineering-handoff/install
Agent should check
- Task fit and alternatives from Resolve API.
- Audit score, trust score, and safety policy warnings.
- Install target compatibility for Codex, Claude Code, Cursor, or CLI.
Copy prompt
Task: Use handoff in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20handoff%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/darkroomengineering-handoff/install
Install command: npx skills add darkroomengineering/cc-settings --skill handoff
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.Agent handoff
Give an agent the install path, not another directory page.
Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.
Install handoff
/api/skills/darkroomengineering-handoff/install
LLM text format
/api/skills/darkroomengineering-handoff/install?format=text
Find alternatives
/api/skills/search?q=handoff&limit=3
Agent prompt
Use handoff for this task. Review https://www.openagentskill.com/api/skills/darkroomengineering-handoff/install, then install with: npx skills add darkroomengineering/cc-settings --skill handoffRegistry metadata
Agent-readable profile for automatic skill selection.
This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.
Manifest
/api/registry/manifest/darkroomengineering-handoff
LLM text
/api/registry/manifest/darkroomengineering-handoff?format=text
Install alias
/api/registry/install/darkroomengineering-handoff
Recommend
/api/registry/recommend?task=Use%20handoff%20in%20an%20agent%20workflow&limit=3
Agent fit
Research agents
Use-case tags
Platforms
Claude Code, OpenAI Agents
Audit report
Needs review · 76/100
A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.
Agent decision cockpit
Fallback candidate for Research agents
Prototype with this skill first; keep a fallback candidate ready.
Role in stack
Fallback candidate
Primary fit
Research agents
Trust label
Prototype first
Install path
Command ready
Use when
- Research agents workflows
- Claude Code teams
- builders willing to evaluate younger projects
Evidence
- recent repository activity
- install command or GitHub repo available
- 63/100 quality profile
review first
- Low GitHub adoption signal
- No OpenAgentSkill engagement data yet
Implementation path
- 1Install it in a sandbox agent and run one Research agents task end to end.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.
Trust profile
Sandbox only
Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
GitHub adoption
CHECK42 GitHub stars
Stars/forks activity
CHECK42 stars, 3 forks; issue activity unavailable in current metadata
Recent maintenance
PASSPushed today
License clarity
PASSMIT
Good signals
- AI review approved
- Install path is available
- Repository evidence is available
- Recently maintained repository
- Install command has no obvious high-risk pattern
- Outcome loop is ready but needs first real agent run
Review before install
- Financial research output is not financial advice; require human review before any live investment decision.
- Low GitHub adoption signal
- Quality score needs review
- Permission surface needs review: secrets or environment access, shell or command execution
- GitHub adoption: 42 GitHub stars
- Stars/forks activity: 42 stars, 3 forks; issue activity unavailable in current metadata
- Dependency/runtime risk: command execution surface, credential or environment access
- Permission surface: secrets or environment access, shell or command execution
- No real agent outcome reports yet
- Human review required before unattended installation
Recommended action
Run only in a sandbox and compare close alternatives before using it for real work.
Quality profile
Promising candidate for agent workflows
Useful candidate, but compare it with alternatives before adopting.
Workflow fit
Use this skill in these scenarios
Investigate faster
Research agents
I need my agent to research a topic, compare sources, and produce a concise report.
Manage repositories
GitHub automation
I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Workflow fit
Add it to a complete workflow
Find, compare, and synthesize
Research report agent
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Turn skills into distribution
Content growth agent
A workflow for turning newly indexed skills into SEO briefs, social drafts, comparison pages, and reusable publishing workflows.
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Alternative shortlist
Compare before you install
Similar skills that may fit this task.
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
MoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
Cua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
Overview
--- name: handoff argument-hint: "[save|resume]" description: End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "context window", "running out of context", "done for today" (save mode); "continue where we left off", "pick up where", "last session", "previous work", "resume" (resume mode). context: fork ---
# Session Handoff
Two-mode skill: **Save** state at end of session, **Resume** state at start of next session.
## Product-aware runner and state
Claude uses the installed runner and state under `~/.claude`:
```bash HANDOFF_RUNNER="$HOME/.claude/src/scripts/handoff.ts" CC_STATE_ROOT="$HOME/.claude" ```
Standalone Codex uses `${CODEX_HOME:-$HOME/.codex}/darkroom/source/src/scripts/handoff.ts`, but the plugin's stable handoff state is exposed only to hooks as `$PLUGIN_DATA`. In a Codex plugin hook, set `HANDOFF_RUNNER` to that runner and `CC_STATE_ROOT="$PLUGIN_DATA"`. Outside that environment, do not guess a cache path or write into `~/.claude`: manual Codex create/resume/list/clean is unavailable until the host exposes the same plugin-data path to the session.
## Mode: Save
Save current session state for later resumption. This is the **end-of-session boundary** skill — for mid-task rollback points before risky operations, use `/checkpoint`.
### Usage
```bash CC_SETTINGS_HOME="$CC_STATE_ROOT" bun "$HANDOFF_RUNNER" create ```
Or use the native command: ``` /handoff ```
### What Gets Saved
Every handoff — auto or manual — always captures real, git-derived data at creation time: - **Project**: name, path, current branch - **Pending changes**: `git status --porcelain` (first 20 lines) - **Key files**: uncommitted paths **union** the files the session ledger observed being changed (see below) - **Recent commits**: subjects of the last 3 commits - **Source**: `manual` or `auto` (see below)
In Claude, three additional sections are built purely from **observed** tool activity, not inference: - **Files Modified** — every path a `Write`/`Edit`/`NotebookEdit` touched - **Files Read** — every path a `Read` touched - **Tool Failures** — the exact tool name and error string, bounded and secret-redacted
These Claude-only sections come from the session ledger, a bounded JSONL at `~/.claude/tmp/session-ledger/<session_id>.jsonl` written by the `PostToolBatch` hook. It exists to fix a specific hole: **`git status` forgets everything you committed.** A file edited at the start of a long session and committed an hour later is invisible to a `git status`-only handoff, so the longer the session, the more of its work disappears from the record. The ledger stores paths, tool names, and error strings only — never file contents, prompts, or tool responses — and never infers, so a `Bash` command's success is recorded as *nothing* rather than as a guess.
Beyond that, what's actually filled in depends on how the handoff was created:
- **Manual** (`/handoff`, or `handoff.ts create --summary "text"`) — the `--summary` text becomes the Session Summary. Active Todos / Current Task / Notes for Next Session are placeholders (`<!-- ... -->`) for you (or the agent, before the turn ends) to fill in manually — the CLI has no way to know your in-progress todos, decisions, or learnings on its own. - **Automatic** (PreCompact/SessionEnd hooks call `create --from-hook`, `source: "auto"`) — Active Todos, Current Task, and Notes for Next Session stay as unfilled placeholders, but **Session Summary is no longer blank on the compaction path**: the `PostCompact` hook writes Claude Code's own `compact_summary` into the handoff that the preceding `PreCompact` created, matched on session id. That summary is the one record of intent, decisions, and rationale; the ledger sections are the record of artifacts. They are stored separately and never merged, so nothing inferred is presented as observed.
Standalone Codex hooks capture the git-derived fields through the shared runner, but Codex does not provide Claude's PostToolBatch session ledger or PostCompact `compact_summary` backfill. Do not claim those sections were observed in Codex.
On a Claude `SessionEnd` handoff (no compaction involved) Session Summary can still be empty — pair it with the structured compaction template below, or run a manual `/handoff` with `--summary` before ending a session.
### GitHub Issue Sync
If the current branch is linked to a GitHub Issue (e.g., `feat/123-description`):
1. **Post a progress comment** on the issue: ```bash gh issue comment 123 --body "## Session Update - Completed: [summary of work done] - Files modified: [list] - Next steps: [what remains]" ```
2. **Check off completed tasks** in the issue body if any task checkboxes were resolved during this session.
This ensures project progress is visible to the whole team, not just in local handoff files.
### Handoff Location
Handoffs are scoped per project (repo toplevel basename, or cwd basename outside a git repo) — a handoff saved in one project never surfaces as "latest" when you resume in another. Claude stores them below `~/.claude/handoffs`; Codex plugin hooks store them below `$PLUGIN_DATA/handoffs`:
``` ~/.claude/handoffs/ └── <project-name>/ ├── handoff_20260115_143000.md ├── handoff_20260115_143000.json ├── latest.md -> handoff_20260115_143000.md └── ... ```
Handoffs saved before this per-project scoping existed live under the flat `~/.claude/handoffs/` directory; `resume`/`list` fall back to that legacy directory exactly once, only when the current project has no scoped store of its own yet.
### When to Create Handoff
1. **End of work session** - Before closing Claude Code 2. **Context at 65%+** - Before manual compaction or context quality degrades 3. **Taking a break** - Preserve state for later 4. **Switching tasks** - Save before context switch 5. **Before compacting** - Auto-triggered by PreCompact hook
### Auto-Handoff
Both products create git-derived handoffs before compaction and at session end. Claude additionally provides the session-ledger and PostCompact behavior described above. Codex does not provide Claude's SessionStart handoff display or automatic pruning contract; do not promise either.
### Output
Confirms: - Handoff file created (and GitHub Issue updated if linked) - Location of file - Key information saved
---
### Claude context-window runbook (folded in from former `/context` skill)
The statusline shows live context usage:
``` Opus 5 | my-project | main*↑ | ▊░░░░░░░░░ 8% (84k/1.0M) ```
| Usage | Action | |-------|--------| | 65–79% | Save a checkpoint and compact or prepare a handoff | | 80–89% | Stop expanding scope and run `/handoff` | | 90%+ | Run `/handoff` **now** |
#### Model degradation thresholds
Degradation is not gradual — it follows a step function. Place critical information at the beginning and end — see `AGENTS.md` "Context Hygiene". Avoid burying key facts in the middle.
| Model | Noticeable degradation | Severe degradation | |-------|------------------------|--------------------| | Claude Opus 5 | ~100K tokens | ~180K tokens | | Claude Sonnet 5 | ~80K tokens | ~150K tokens | | Claude Haiku 4.5 | ~50K tokens | ~90K tokens |
Sonnet 5's tokenizer is ~30% heavier than Sonnet 4.6's, so it reaches these thresholds on noticeably less actual text — the token counts above are unchanged, but the same conversation fills them faster.
**Key patterns:** - **Lost-in-middle** — information in the center gets less attention - **Context poisoning** — a single wrong fact can corrupt reasoning on related topics - **Context distraction** — irrelevant info degrades performance on a step function, not proportionally
#### Structured compaction template
When compaction is unavoidable, populate this template — each section forces preservation of the dimensions most often lost:
```markdown ## Session Intent [What the user is trying to accomplish — the "why"]
## Files Modified - path/to/file.ts: What changed and why
## Files Read (Not Modified) - path/to/reference.ts: Why it was consulted
## Decisions Made - Decision 1: Rationale
## Errors Encountered - Error message → Resolution applied (or "still unresolved")
## Current State - Build status / test status / what works / what doesn't
## Next Steps 1. Immediate next action 2. Following action ```
The artifact trail (which files were touched, what changed) is universally the weakest dimension after compression. Dedicated sections force preservation of file paths, error messages, and decisions that would otherwise silently drift away.
#### Post-compaction validation
After compaction, probe 3–5 critical facts before continuing work:
1. "What files have I modified in this session?" 2. "What was the last error I encountered?" 3. "What approach did I decide on and why?" 4. "What are the remaining next steps?"
If any probe returns vague or incorrect answers, re-read the handoff file (`/handoff` resume mode) to restore critical context.
#### Reducing context proactively
1. **Use `context: fork`** — skills that fork don't bloat main context 2. **Delegate exploration** — let agents handle research 3. **Clean summaries** — agents return summaries, not raw output 4. **Avoid large file reads** — use TLDR for token-efficient analysis 5. **Offload large tool output** — write outputs >2000 tokens to scratch files; return summary + path 6. **Place critical info at edges** — beginning and end of context get more attention
---
## Mode: Resume
Load state from a previous session and continue work.
### Usage
```bash CC_SETTINGS_HOME="$CC_STATE_ROOT" bun "$HANDOFF_RUNNER" resume ```
Or use: ``` /handoff resume ```
### What Gets Loaded
- **Previous task**: What you were working on - **Progress**: What was completed - **Decisions**: Key choices made - **Files modified**: What was changed - **Next steps**: What remains - **Context**: Important information
### GitHub Issue Context
Before loading the local handoff, check for a linked GitHub Issue:
```bash BRANCH=$(git branch --show-current) ISSUE_NUM=$(echo "$BRANCH" | grep -oE '[0-9]+' | head -1)
if [[ -n "$ISSUE_NUM" ]]; then gh issue view "$ISSUE_NUM" --comments fi ```
If an issue is found, **present it as the primary context** — it's the shared source of truth. The local handoff supplements it with session-specific details.
Present a combined summary: - **From GitHub Issue**: Title, task progress (X/Y done), latest comments - **From local handoff**: Session-specific notes, open files, debug state
### Available Handoffs
In Claude, list handoffs for the current project: ```bash ls ~/.claude/handoffs/"$(basename "$(git rev-parse --show-toplevel 2>/dev/null || pwd)")"/ ```
### Resume Options
#### Most Recent ``` /handoff ``` Loads the most recent handoff for current project.
#### Specific Handoff ``` /handoff project-name-2024-01-15-1430 ``` Loads a specific handoff file.
#### List All ``` /handoff list ``` Shows available handoffs.
#### Clean Old Handoffs ```bash CC_SETTINGS_HOME="$CC_STATE_ROOT" bun "$HANDOFF_RUNNER" clean [keep] ``` Removes old handoff files, keeping the most recent `keep` (default: 20) of each type (`.json` and `.md`). SessionStart already prunes down to 20 automatically on every session, so this is only needed for on-demand cleanup (e.g. `clean 0` to wipe all handoffs).
### Workflow
1. **Check GitHub Issue** - Read linked issue for shared project context 2. **Load local handoff** - Read session-specific state 3. **Review combined context** - Understand where we left off 4. **Verify files** - Check current state vs handoff 5. **Continue work** - Pick up next steps from the issue task list
### Claude automatic session start
When starting a new session, the setup automatically: - Checks for linked GitHub Issue (reads context) - Recalls project learnings - Shows recent handoff if available - Displays context from previous work
Technical details
- Version
- 1.0.0
- License
- MIT
- Last updated
- Aug 24, 2026
- Published
- Aug 24, 2026
Decision snapshot
Fallback candidate
recent repository activity
Audit
Install review
Install and adoption review
- Security
- 77/100
- Maintenance
- 100/100
- Install
- 92/100
Agent-proven evidence
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
- Success rate
- —
- Recent failure
- —
- Outcomes
- 0
- Output quality
- —
- Failed
- 0
- Not relevant
- 0
- Installs
- 0
- Risk blocked
- 0
- Setup needed
- 0
- Production
- 0
No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.
Install
Add to agent workflow
Free and open source. Review the report before installing into production agents.
Growth loop
Share kit
Scenario-led draft for handoff, ready for a manual X post.
handoff: End-of-session save and next-session resume. Triggers "ending session", "wrapping up", "conte... 42 stars https://www.openagentskill.com/skills/darkroomengineering-handoff?ref=x
Optional reply with install command
Listing + install path for handoff: https://www.openagentskill.com/skills/darkroomengineering-handoff?ref=x Install: npx skills add darkroomengineering/cc-settings --skill handoff
Listing source
Registry indexed
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
- Creator
- darkroomengineering
- Indexed by
- OpenAgentSkill community index
Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.
Claim this skillOwner claim
Claim this skill listing
This Registry indexed listing is attributed to darkroomengineering but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.
Creator backlink kit
Add the evidence badges to your README
Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.
[](https://www.openagentskill.com/skills/darkroomengineering-handoff)
[](https://www.openagentskill.com/skills/darkroomengineering-handoff)
[](https://www.openagentskill.com/skills/darkroomengineering-handoff/audit)
[](https://www.openagentskill.com/skills/darkroomengineering-handoff)Author
darkroomengineering
@darkroomengineering
Tags
Platform fit
Health signals
- GitHub stars
- 42
- Quality score
- 35/100
- Last GitHub push
- Aug 24, 2026
- Framework hints
- Unknown
- OpenAgentSkill views
- 0
- Install copies
- 0
- Outbound clicks
- 0
Community signal
Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.
Trust & safety
Sandbox only
- GitHub adoption42 GitHub starsCHECK
- Stars/forks activity42 stars, 3 forks; issue activity unavailable in current metadataCHECK
- Recent maintenancePushed todayPASS
- License clarityMITPASS
- README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
- Dependency/runtime riskcommand execution surface, credential or environment accessCHECK
Related skills
UI-TARS Desktop
Run multimodal agents that operate desktop interfaces
37.0K StarsMoneyPrinterTurbo
利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.
88.5K StarsCua
Open-source infrastructure for Computer-Use Agents. Sandboxes, SDKs, and benchmarks to train and evaluate AI agents that can control full desktops (macOS, Linux, Windows).
21.4K Stars