@LocalSymmetry

Creator · LocalSymmetry

Last updated · Aug 24, 2026

lofn-step11-packager

REVIEW · 57Registry indexed

Build complete Step 11 refinement prompt bundles (the "fable packager") for a Lofn music run — full personality YAML + Suno v5.5 rules + golden songs + full run context + step-10 (and any prior step-11 draft) + the canonical Manual Refinement Instructions, as paste-ready 120-200K

OpenAgentSkill Trust Score
57/100

Do not auto-install

Quality55/100
Audit71/100
Stars22
Verified installs0

Install targets

Codex install prompt

Install the "lofn-step11-packager" agent skill from https://github.com/LocalSymmetry/lofn/tree/main/.agents/skills/lofn-step11-packager. 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: Build complete Step 11 refinement prompt bundles (the "fable packager") for a Lofn music run — full personality YAML + Suno v5.5 rules + golden songs + full run context + step-10 (and any prior step-11 draft) + the canonical Manual Refinement Instructions, as paste-ready 120-200KB prompt files for Codex-Fable/Opus refinement. Use when the user asks to "package step 11", build fable/opus refinement prompts, or assemble the full-context refinement bundle for a finished run's pairs. Do NOT use to run the inline pipeline (that's lofn-music) or to render audio. 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":"localsymmetry-lofn-step11-packager","task":"Install lofn-step11-packager","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.

Browse track

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 LocalSymmetry/lofn --skill lofn-step11-packager

Maintenance

fresh

Pushed today

Risk

Needs review

License is unclear

GitHub quality

22

55/100 Quality · 65/100 Trust

Coverage tags

CodingGitHub automationdesign-creativeagent-skill

Review notes

License is unclear · Repository license is listed as 'Unknown' by GitHub; no explicit license file is present in the skill directory or referenced in SKILL.md, which creates ambiguity about usage rights.

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

Promising
55

Useful candidate, but compare it with alternatives before adopting.

Trust

Do not auto-install
57

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

Audit

Needs review
71

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Choose a stronger alternative or inspect the source manually before any install attempt.

CodexClaude CodeCursorOpenAgentSkill CLI

Stars

22 GitHub stars

Repo activity

22 stars, 1 forks

Maintenance

Pushed today

License

Unknown

Install

npx skills add LocalSymmetry/lofn --skill lofn-step11-packager

Install safety

standard package or runtime install path

Permission surface

shell or command execution, filesystem or document access

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • Repository license is listed as 'Unknown' by GitHub; no explicit license file is present in the skill directory or referenced in SKILL.md, which creates ambiguity about usage rights.
  • License is unclear
  • Low GitHub adoption signal
  • Quality score needs review

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is unclear
  • 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+

Suited tasks

  • Research agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Search sources

Suited agents

CodexClaude CodeCursorOpenAgentSkill CLIOpenAI AgentsCLI

Install decision

Command
npx skills add LocalSymmetry/lofn --skill lofn-step11-packager
Policy
review
Human review
yes

Trust and risk

Trust
57/100
Audit
71/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add LocalSymmetry/lofn --skill lofn-step11-packager

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Low GitHub adoption signal
  • Repository license is listed as 'Unknown' by GitHub; no explicit license file is present in the skill directory or referenced in SKILL.md, which creates ambiguity about usage rights.
  • No OpenAgentSkill engagement data yet

Agent safety v2

39/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Browser automation

Skill may drive a browser or interact with web pages.

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-risk permission hints: Shell or command execution
  • License is unclear

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 text plan

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 lofn-step11-packager in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20lofn-step11-packager%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/localsymmetry-lofn-step11-packager/install
Install command: npx skills add LocalSymmetry/lofn --skill lofn-step11-packager
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.

Open install API

Agent prompt

Use lofn-step11-packager for this task. Review https://www.openagentskill.com/api/skills/localsymmetry-lofn-step11-packager/install, then install with: npx skills add LocalSymmetry/lofn --skill lofn-step11-packager

Registry 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.

Open manifest

Agent fit

54/100

Research agents

Platforms

Claude Code, OpenAI Agents

Audit report

Needs review · 71/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Needs validation for Research agents

Do a manual repository review before adding this to an agent workflow.

54
Readiness
Review
Stage

Role in stack

Needs validation

Primary fit

Research agents

Trust label

Needs manual review

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
  • 55/100 quality profile

review first

  • Low GitHub adoption signal
  • Repository license is listed as 'Unknown' by GitHub; no explicit license file is present in the skill directory or referenced in SKILL.md, which creates ambiguity about usage rights.
  • No OpenAgentSkill engagement data yet

Implementation path

  1. 1Install it in a sandbox agent and run one Research agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Do not auto-install

Trust Score v5 found insufficient evidence for agent installation. Treat this as discovery material, not an executable recommendation.

57
OpenAgentSkill Trust Score

GitHub adoption

FIX

22 GitHub stars

Stars/forks activity

FIX

22 stars, 1 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

Pushed today

License clarity

CHECK

Unknown

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

  • Repository license is listed as 'Unknown' by GitHub; no explicit license file is present in the skill directory or referenced in SKILL.md, which creates ambiguity about usage rights.
  • License is unclear
  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 22 GitHub stars
  • Stars/forks activity: 22 stars, 1 forks; issue activity unavailable in current metadata
  • License clarity: Unknown
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Choose a stronger alternative or inspect the source manually before any install attempt.

Quality profile

Promising candidate for agent workflows

Useful candidate, but compare it with alternatives before adopting.

55
GitHub stars
22
Freshness
Today
Install ready
Yes
License
Unknown
Review before install: Low GitHub adoption signal · Repository license is listed as 'Unknown' by GitHub; no explicit license file is present in the skill directory or referenced in SKILL.md, which creates ambiguity about usage rights.

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

--- name: lofn-step11-packager description: Build complete Step 11 refinement prompt bundles (the "fable packager") for a Lofn music run — full personality YAML + Suno v5.5 rules + golden songs + full run context + step-10 (and any prior step-11 draft) + the canonical Manual Refinement Instructions, as paste-ready 120-200KB prompt files for Codex-Fable/Opus refinement. Use when the user asks to "package step 11", build fable/opus refinement prompts, or assemble the full-context refinement bundle for a finished run's pairs. Do NOT use to run the inline pipeline (that's lofn-music) or to render audio. ---

# Lofn Step 11 Packager — Codex-backed fable/opus refinement-prompt builder

> **⚖️ AUTHORITY (2026-07-01):** the `.claude/skills/` twin of this skill is the CANONICAL policy source; this Codex mirror binds to it and to `.agents/skills/lofn/EXECUTION.md` §8 (Policy Deltas — golden-output quarantine, no-skip/NON-CANONICAL, itemized packet, per-pair variation angles, judge separation, the publish bar, gate mid-bands). On any disagreement, the `.claude` file wins.

Assembles the **full** context bundle for a Lofn music run into one paste-ready prompt per pair, so a high-capability model (Codex‑Fable 5 / Opus) can re-produce the Step 11 enhanced Suno package with complete creative authority. Each prompt embeds: the entire archive personality YAML (~50KB), the Suno v5.5 construction rules, the golden songs index, the full run context (seed → panel debate → metaprompt → pair assignments → creative context/ICB), the production mandates, the **Step 10** package (and any prior inline **Step 11** draft), and — as the final block — the canonical **Manual Refinement Instructions** (the executable task).

This is the Codex-native port of the legacy `skills/step11-packager/`. It is **self-contained**: the packager-specific references (Suno v5.5 rules, golden songs index, the default LOFN-PRIME YAML) are vendored under `references/` so the skill runs even outside the repo. The repo archive is only a fallback for **named** personalities not vendored here. This skill swaps the **execution layer**: vendored/repo-relative paths, the Codex-native run layout, and cross-platform (Windows, UTF-8) I/O. The legacy `skills/step11-packager/` is left untouched. See `.agents/skills/lofn/EXECUTION.md`.

## When to use vs. lofn-music - **lofn-music** runs the pipeline 00→11 inline (it already produces `pair_NN_step10_final_package_enhanced.md`). - **This skill** is the *manual-refinement packager*: it does not generate songs. It wraps a finished (or partway) run's per-pair Step 10 outputs into the heavy refinement prompt so the smart model can rebuild Step 11 from scratch with all context in one paste — for a deeper polish pass, a Fable/Opus rerun, or a head-to-head against the inline step-11 draft.

## Primary workflow — scripted (recommended)

`scripts/build_fable_prompt.py` auto-discovers everything from the run directory. On this machine the interpreter is `python` (Python 3.14).

```bash # Build all pairs for a run (auto-detect repo root, pairs, personalities, context): python .agents/skills/lofn-step11-packager/scripts/build_fable_prompt.py output/daily/2026-06-19

# Opus-named variant: python .agents/skills/lofn-step11-packager/scripts/build_fable_prompt.py output/daily/2026-06-19 --mode opus

# Specific pairs only: python .agents/skills/lofn-step11-packager/scripts/build_fable_prompt.py output/daily/2026-06-19 --pairs 1,3,5

# Override personality (archive filename or absolute path) / custom output / explicit repo root: python .agents/skills/lofn-step11-packager/scripts/build_fable_prompt.py output/daily/2026-06-19 --personality lofn-prime-mini.yaml python .agents/skills/lofn-step11-packager/scripts/build_fable_prompt.py output/daily/2026-06-19 -o /tmp/prompts python .agents/skills/lofn-step11-packager/scripts/build_fable_prompt.py output/daily/2026-06-19 --repo-root E:/git/lofn ```

**What it does:** 1. Auto-detects the repo root (from the script location, then the run dir) — no hardcoded workspace path. 2. Discovers per-pair Step 10 files: `<run>/music/pair_NN_step10_package.md` (Codex-native) or `<run>/audio/pair_XX_step10_production_wrap.md` (legacy) — backslash-safe. 3. Resolves each pair's personality from `05_pair_assignments.md` (LOFN-PRIME AWE/INDIGNATION mode by default; a named personality maps to its archive YAML; otherwise LOFN-PRIME). 4. Embeds the full personality YAML, the Suno rules, and the golden songs index — **vendored copies in this skill's `references/` are used first**; for a named personality not vendored, it falls back to the repo archive `skills/orchestration/personalities/` if present. 5. Embeds the full run context (research brief, golden seed, panel debate, metaprompt, pair assignments, creative context/ICB) and the production mandates. 6. Embeds the full Step 10 package and, if present, the prior inline Step 11 draft (`pair_NN_step10_final_package_enhanced.md`) as "improve on this" (suppress with `--no-enhanced`). 7. Appends the canonical Manual Refinement Instructions (three-block output spec, Disc_Channel + EMO format, <5000-char lyrics cap) as the FINAL block. 8. Writes `<run>/music/pair_NN_step11_{fable|opus}_prompt.md` per pair, in UTF-8.

## Then: execute the refinement (Codex-native) The packager only builds the prompt — it does not call any model. To produce the enhanced package, hand each `pair_NN_step11_*_prompt.md` to the refinement engine: - **Subagent (default):** spawn one Agent per pair (model `fable` for the Fable-5 ceremony tier, or inherit Opus), feeding it the prompt file as its task. It returns the three-block enhanced package. - **Manual:** paste a file into a Codex‑Fable/Opus chat for a hand pass.

The model's output MUST be the three canonical blocks (`## SUNO STYLE PROMPT` 850–1000 chars · `## SUNO EXCLUDE PROMPT` 400–900 chars · `## SUNO ENHANCED LYRICS` with `[Theme:]`+`[SONG FORM:]`, 5-line Disc_Channel strip, em-dash EMO section headers, entire lyrics field **< 5000 chars**) plus every supporting block. Save as `pair_NN_step11_enhanced_suno.md`, then route through **lofn-qa**.

## Fallback workflow — manual build If the script can't run, assemble by hand per the legacy spec in `skills/step11-packager/SKILL.md` §"Fallback Workflow" — same mandatory inclusions, but read context from the Codex-native filenames (`core_seed.md`, `03_panel_debate.md`, `04_metaprompt.md`, `05_pair_assignments.md`, `CREATIVE_CONTEXT.md`) and Step 10 from `<run>/music/pair_NN_step10_package.md`.

## Mandatory inclusions (every prompt file) 1. Context header (run, run ID, pair, personality, mode) 2. **Full personality YAML — the ENTIRE file, zero bytes trimmed** (LOFN-PRIME = `lofn-prime-mini.yaml`, ~1800 lines) 3. Full Suno v5.5 construction rules (7 principles + 7-position order + limits + format) 4. Full run context — never rely on the reviewer opening repo files 5. Golden Song References index (two examples with payloads) 6. Production mandates — full text, not summaries 7. **Full Step 10 output** — all sections, not just music prompt + lyrics 8. Prior Step 11 draft if it exists (improve, don't echo) 9. **Manual Refinement Instructions as the FINAL block** — the executable task

## Anti-patterns — never do these - ❌ Abbreviated personality block instead of the full YAML file - ❌ Extracting only "music prompt + lyrics" from Step 10 - ❌ Truncating files with "[… truncated …]" markers - ❌ Building prompts under 50KB (the script warns) — the YAML alone is ~50KB; a real bundle is **120–200KB**

## ⛔ FUSION IS PERMANENTLY BANNED OpenRouter Fusion (`openrouter/fusion`) drained all OpenRouter credits. Never invoke, mention, offer, or build Fusion-mode prompts. There is no `--mode fusion`. The refinement engine is Codex (Fable/Opus) only.

## References **Vendored (self-contained, used first):** - `references/suno_rules_condensed.md` — Suno v5.5 rules (embedded by the script) - `references/golden_songs_index.md` — golden song payloads - `references/personalities/lofn-prime-mini.yaml` — the default LOFN-PRIME DNA (daily/fallback persona)

**Repo fallback (for named personalities not vendored, non-destructive):** - `skills/orchestration/personalities/*.yaml` — full archive personality DNA. To make a named-personality run self-contained too, copy its YAML into `references/personalities/`. - `skills/step11-packager/SKILL.md` — the legacy spec this port mirrors

Technical details

Version
1.0.0
License
Unknown
Last updated
Aug 24, 2026
Published
Aug 24, 2026

Decision snapshot

Needs validation

54
Ready
Review
Stage

recent repository activity

Audit

Install review

Install and adoption review

71
Needs review
Security
70/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
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

X

Scenario-led draft for lofn-step11-packager, ready for a manual X post.

Curator note
lofn-step11-packager: Build complete Step 11 refinement prompt bundles (the "fable packager") for a Lofn music run...

22 stars

https://www.openagentskill.com/skills/localsymmetry-lofn-step11-packager?ref=x
Open X draft
Optional reply with install command
Listing + install path for lofn-step11-packager:
https://www.openagentskill.com/skills/localsymmetry-lofn-step11-packager?ref=x

Install: npx skills add LocalSymmetry/lofn --skill lofn-step11-packager

Listing source

Registry indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

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 skill

Owner claim

Claim this skill listing

This Registry indexed listing is attributed to LocalSymmetry 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.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/localsymmetry-lofn-step11-packager?metric=listed&label=Listed)](https://www.openagentskill.com/skills/localsymmetry-lofn-step11-packager)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/localsymmetry-lofn-step11-packager?metric=trust&label=Trust)](https://www.openagentskill.com/skills/localsymmetry-lofn-step11-packager)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/localsymmetry-lofn-step11-packager?metric=audit&label=Audit)](https://www.openagentskill.com/skills/localsymmetry-lofn-step11-packager/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/localsymmetry-lofn-step11-packager?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/localsymmetry-lofn-step11-packager)

Author

L

LocalSymmetry

@localsymmetry

Health signals

GitHub stars
22
Quality score
32/100
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

Do not auto-install

57
  • GitHub adoption22 GitHub starsFIX
  • Stars/forks activity22 stars, 1 forks; issue activity unavailable in current metadataFIX
  • Recent maintenancePushed todayPASS
  • License clarityUnknownCHECK
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskcommand execution surfaceINFO