sync-skill-cache SKILL.md skillA

sync-skill-cache from hyhmrright/logic-lens is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add hyhmrright/logic-lens/sync-skill-cache@git:20260601.6510174

Pins git:20260601.6510174 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
hyhmrright/logic-lens
Path
.claude/skills/sync-skill-cache/SKILL.md
Versions recorded
1
Latest version
git:20260601.6510174, committed Jun 1, 2026
Size
2,110 bytes
Repository stars
25
License
MIT

Sync the Logic-Lens working-copy skills/ into the installed plugin cache so content-evals test the EDITED skill, not the last published one. ALWAYS run this after editing any skills/**/SKILL.md or guide/_shared file and BEFORE running content-evals — otherwise the eval silently grades stale content and every token is wasted. Also use to verify the cache is in sync ("is the cache fresh?", "did my edit take effect in evals?", "check skill cache drift").

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# sync-skill-cache

content-evals invoke each skill through Claude Code's plugin mechanism, which loads from
`~/.claude/plugins/cache/logic-lens-marketplace/logic-lens/<version>/skills/` — **not** the
repo's `skills/`. Editing `skills/` changes nothing the eval sees until you copy it into the
cache. This is the single most expensive footgun in the iteration loop: skip it and you grade
the previous skill while believing you tested your change.

## Steps

1. **Sync + verify** from the repo root:
   ```bash
   bash .claude/skills/sync-skill-cache/scripts/sync-cache.sh
   ```
   The script reads the active version from `package.json`, rsyncs `skills/` into the matching
   cache dir (`--delete`, so removed files are removed in the cache too), then diffs the two to
   confirm they are byte-identical. It prints `OK …` on success.

2. **If it prints `DRIFT` or a missing-cache error:** do not run evals. The two common causes:
   - The cache dir for the current `package.json` version doesn't exist (plugin not installed at
     this version) — reinstall/refresh the plugin, or check you didn't just bump the version
     without refreshing the cache.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add hyhmrright/logic-lens/sync-skill-cache@sha256:5818174e89aaf581

The line at the top of this page pins the label git:20260601.6510174, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_5h6xa5kc2bbj5gao.svg)](https://markdownregistry.com/a/art_5h6xa5kc2bbj5gao)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Jun 1, 2026.

versioncommittedcommitsizeaudit
git:20260601.6510174 latest2026-06-01 6510174 2,110 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2110 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

hyhmrright/logic-lens · 25 stars · license MIT · pushed 2026-10-30 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5h6xa5kc2bbj5gao
GET https://markdownregistry.com/api/v1/resolve?ref=hyhmrright/logic-lens/sync-skill-cache
GET https://markdownregistry.com/api/v1/blob/5818174e89aaf5817ebbafca2f2f9cd8cd59070448f83df7dcc6fc7280abc2a5

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from hyhmrright/logic-lens

bump-version SKILL.md skill
hyhmrright/logic-lens · .claude/skills/bump-version/SKILL.md · Bump the Logic-Lens version across all six metadata locations at once (package.json, the four plugin manifests, and the…
git:20260528.2e39bfc · audit A · 25 stars
iterate-skill SKILL.md skill
hyhmrright/logic-lens · .claude/skills/iterate-skill/SKILL.md · Run the Logic-Lens skill-improvement loop end to end — baseline → diagnose failures → edit → sync cache → re-eval →…
git:20260601.6510174 · audit A · 25 stars
new-skill SKILL.md skill
hyhmrright/logic-lens · .claude/skills/new-skill/SKILL.md · Scaffold a new logic-* skill in the Logic-Lens repo and wire it into every place a skill must be registered, so no step…
git:20260528.2e39bfc · audit A · 25 stars
run-iteration-eval SKILL.md skill
hyhmrright/logic-lens · .claude/skills/run-iteration-eval/SKILL.md · Run the Logic-Lens content-eval pipeline for one iteration and produce a scored summary.json — use to measure a skill…
git:20260601.6510174 · audit A · 25 stars
AGENTS.md AGENTS.md file
hyhmrright/logic-lens · AGENTS.md
git:20261029.59e74ed · audit A · 25 stars
CLAUDE.md CLAUDE.md file
hyhmrright/logic-lens · CLAUDE.md
git:20261029.59e74ed · audit A · 25 stars
logic-diff SKILL.md skill
hyhmrright/logic-lens · skills/logic-diff/SKILL.md · Compare two code versions for semantic equivalence via semi-formal tracing of both versions side-by-side. Trigger when…
git:20260515.1220707 · audit A · 25 stars
logic-explain SKILL.md skill
hyhmrright/logic-lens · skills/logic-explain/SKILL.md · Explain what a specific piece of code actually does for a given input by producing a step-by-step execution trace…
git:20260507.46cac5d · audit A · 25 stars
logic-fix-all SKILL.md skill
hyhmrright/logic-lens · skills/logic-fix-all/SKILL.md · Autonomous repository-wide audit-and-fix pipeline: health → review → locate/explain → fix → diff-verify → iterate until…
git:20260507.46cac5d · audit A · 25 stars
logic-health SKILL.md skill
hyhmrright/logic-lens · skills/logic-health/SKILL.md · Sweep a directory, module, or full codebase for logic correctness and produce a scored health dashboard with systemic…
git:20260507.46cac5d · audit A · 25 stars
logic-locate SKILL.md skill
hyhmrright/logic-lens · skills/logic-locate/SKILL.md · Locate the root cause of a CONFIRMED failure via backward-then-forward semi-formal tracing. Trigger when the user…
git:20260515.1220707 · audit A · 25 stars
logic-review SKILL.md skill
hyhmrright/logic-lens · skills/logic-review/SKILL.md · Find logic bugs in a single file or function via semi-formal execution tracing (Premises → Trace → Divergence → Trigger…
git:20260808.69de591 · audit A · 25 stars

Every file in hyhmrright/logic-lens

Browse by kind, by grade A, or by owner.