asset-placement-gate
Routes a proposed skill, plugin, or agent to its correct home — forge-harness (FH) meta-skill, project-local agent, or drop — by applying a 4-criteria meta-skill bar followed by a project-local value test.
chrono-meta · AI review on file
Installation
Read the source and dependencies before running a command. Copying does not install or execute anything.
npx skills add chrono-meta/forge-harness --skill asset-placement-gateAbout this skill
name: asset-placement-gate description: Routes a proposed skill, plugin, or agent to its correct home — forge-harness (FH) meta-skill, project-local agent, or drop — by applying a 4-criteria meta-skill bar followed by a project-local value test. user-invocable: true allowed-tools: ["Read", "Grep", "Glob", "Bash"] model: sonnet
asset-placement-gate
Routes new skills, agents, and plugins to the correct location when proposed.
Triggers
- "Should I make this an FH skill?"
- "Where should I put this agent?"
- When a new FH asset creation is proposed
/asset-placement-gate {asset name or description}
Natural Language Triggers (example user phrases)
When unsure where to place a new asset or skill:
| Example phrase | Intent |
|---|---|
| "Should I put this in a separate file?" | Asset necessity + placement decision |
| "Can this pattern be shared across projects?" | FH cross-project value assessment |
| "Is this only for our project, or can others use it too?" | cross-project vs local routing |
| "What if I turn this into a skill and use it across projects?" | FH 4-criteria trigger |
| "Where should I put this agent if I want to share it?" | Placement routing needed |
| "Should I extract this to a separate file, or leave it?" | Asset necessity + placement decision |
| "I'd like to manage this as a shared resource" | Cross-project shared management review |
| "Decide whether this stays local or is available to other teams too" | cross-project vs local routing |
| "I don't know where to save this" | Placement routing needed |
| "Should this become a shared asset?" | FH 4-criteria trigger |
Execution Order (summary)
- Request full file path from user (or accept natural language description)
- Load asset content via
Read(if path provided) 2.5. Step 0.5 mechanical overlap pre-scan (grounds criterion ④) + Step 0.6 official-corpora check (grounds criterion ③) - Evaluate Step 1 4-criteria in order (LLM makes the judgment, ④ gated on the Step 0.5 scan, ③ informed by Step 0.6)
- ① + ④ both pass + at least one of ②③ passes → output "FH suitable" Otherwise, proceed to Step 2 local assessment → if fails, output "Project-local agent or no asset needed"
Step 0. Parse Input + Fetch Asset
Immediately after trigger, acquire asset content in the following order.
-
Path provided (contains
.mdor starts with/): Read the file.- If read fails: "File not found. Please verify the path or provide a direct description." — then stop.
-
Description provided (natural language): Check whether all 3 fields can be identified:
- Purpose: What this asset does (1 line)
- Trigger: In what situation is it invoked?
- Expected callers: Which project / which users will use it?
All 3 identifiable → use as asset description. Any 1 unclear → stop with this question:
The asset description is insufficient. Please provide:
- Purpose of this asset (one line)
- In what situation is it invoked?
- Which project/users will primarily use it?
-
No input: Stop with the question below.
Which asset should I evaluate? Enter a file path (e.g.,
.claude/agents/jira-create.md) or a description.
After acquiring the asset content, run Step 0.5 (mechanical overlap pre-scan) and Step 0.6 (official-corpora check) before the judged Step 1.
Step 0.5. Mechanical Overlap Pre-Scan (grounds criterion ④)
Criterion ④ ("no overlap with existing FH skills") is otherwise an LLM recall judgment with no ground truth — a duplicate skill with a novel name passes because the judge has no enumerated list to check against (judge-robustness swarm, 2026-06-13). Ground it mechanically first:
Run this in Bash from the FH repo root (the pipeline below is grep | grep -v | grep -c, which the
Grep tool cannot express).
# LEG A — enumerate existing skill names + descriptions (grounds the judged comparison).
# This leg is ALSO the liveness check for leg B: a dead scan and a genuine no-collision both
# produce collision-count 0, so the enumerate count must be read FIRST.
ROSTER="$(grep -riE 'name:|description:' plugins/fh-meta/skills/*/SKILL.md plugins/fh-commons/skills/*/SKILL.md)"
ROSTER_N="$(printf '%s' "$ROSTER" | grep -c . )"
echo "roster_entries=$ROSTER_N"
if [ "$ROSTER_N" -eq 0 ]; then
echo "SCAN_DEAD — enumerate leg returned 0 rows (wrong cwd / missing plugins tree / glob did not match)."
echo "Criterion ④ = UNDETERMINED. Do NOT read this as 'no collision'. Fix the cwd and re-run."
# fail-closed: stop here, do not run leg B, do not pass ④
fi
# LEG B — hard-collision check (run ONLY when ROSTER_N > 0).
# WHOLE proposed name or a WHOLE trigger phrase reused verbatim.
# grep -wF (whole-word, fixed-string) on the full strings — NOT -E on tokens (a shared common
# word like "review" is not a collision). Exclude the asset's own file (self-match = false hit).
SELF="plugins/fh-meta/skills/PROPOSED_NAME/SKILL.md"
grep -rwF -e "PROPOSED_FULL_NAME" -e "FULL_TRIGGER_PHRASE_1" -e "FULL_TRIGGER_PHRASE_2" \
plugins/*/skills/*/SKILL.md | grep -v "$SELF" | grep -c .
(Replace the PROPOSED_* / FULL_TRIGGER_* tokens with the literal strings under evaluation.)
Surface roster_entries + collision count + nearest existing skill(s) — the roster count is part of
the report, not a private step: collision=0 is only meaningful next to a non-zero roster_entries
(not-found ≠ zero). Criterion ④ then passes only if roster_entries > 0 AND 0 whole-name/
whole-trigger collision AND the judged ≤90%-overlap check agrees. roster_entries = 0 is
SCAN_DEAD → ④ UNDETERMINED (fail-closed), never a pass. A verbatim whole-name or
whole-trigger reuse is a hard ④ fail regardless of the LLM judgment. Honest scope: the grep grounds
literal name/trigger reuse only — a post-cutoff duplicate with a paraphrased trigger is invisible to
both the judge (cutoff) and the grep (literal); that residual leans