Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →m0n0x41d/h-semio-review
INTERNAL SUBROUTINE — semiotic / fanout audit on a concept rename, deprecation sweep, or doc-vs-code consistency check. Walks all carriers (filenames, manifests, stale refs, review surfaces, dashboards, prompts) until fixed-point clean, because one-shot text replacement creates rework when carriers diverge. Manual invocation only. Do not auto-select for general work — for code review use Claude Code review; for FPF reasoning about decisions use h-frame / h-decide.
Passed 16 of 19 test cases with the skill, and 8 of 19 without it.
and 12 more in the full report
11 fixed8 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
After applying the initial batch of file updates for renaming `UserRecord` to `SubjectRecord`, what is the mandatory final verification step before concluding the audit?
| Checked | Without skill | With skill |
|---|---|---|
| Requires re-running carrier discovery until grep queries yield zero unexpected occurrences of the old term. | Missed | Passed |
The instructions your model reads when the skill loads.
You are running the semiotic fanout audit per FPF X-FANOUT-AUDIT and the semiotics_slideument discipline. The premise: on concept rename / deprecation / spec consistency check, the change must sweep ALL carriers — prose, filenames, manifests, review bundles, provenance, tests, schemas — until fixed-point clean. Skipping carriers leaves zombie references that mislead future operators and agents.
Explicit-only — disable-model-invocation: true.
What CONCEPT or TERM is being renamed / deprecated / audited? Get it from the operator explicitly. Bad: "audit the docs"; good: "rename Service to EnablingSystem across docs and code".
If renaming, capture both old and new names. If deprecating, capture the old name and the replacement (or explicit "no replacement").
Run discovery across all carrier surfaces:
# Prose carriers
grep -rl "<term>" --include="*.md" --include="*.txt" --include="*.rst"
# Code carriers
grep -rl "<term>" --include="*.go" --include="*.py" --include="*.ts" --include="*.tsx" --include="*.rs" \
--include="*.java" --include="*.js" --include="*.jsx"
# Manifest carriers
grep -rl "<term>" --include="package.json" --include="Cargo.toml" --include="pyproject.toml" \
--include="go.mod" --include="*.yaml" --include="*.yml" --include="*.toml"
# Filenames
find . -name "*<term>*" -not -path "./node_modules/*" -not -path "./.git/*"
# Test fixtures
grep -rl "<term>" --include="*_test.*" --include="*.test.*" --include="testdata/*"
# Review bundles & specs
grep -rl "<term>" .haft/ docs/ .context/ 2>/dev/null
Build a carrier-by-carrier inventory. Every hit is a potential semio failure if the rename / deprecation doesn't sweep it.
test cases passed, vs 8 / 19 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.