Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ANcpLua/ancplua-claude-plugins --skill derotgit clone --depth 1 https://github.com/ANcpLua/ancplua-claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/derot)<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/derot"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/derot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ancplua/ancplua-claude-plugins/derot"><img src="https://agentmods.dev/badge/skills/ancplua/ancplua-claude-plugins/derot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.01158 |
| Opus 5 | $0.00067 | $0.00579 |
| Sonnet 5 | $0.00027 | $0.00232 |
| Haiku 4.5 | $0.00013 | $0.00116 |
Grade A, and why
derot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
derot — truth-drift auditor
Rot = any place a repo's stated intent has drifted from what the code/build actually is. derot finds it, verifies it against ground truth, and fixes it — correcting where the knowledge is still useful, deleting only what is purely obsolete.
The five rot dimensions
- Comment rot — comments that lie about the code beneath them: stale version numbers, references to renamed/removed symbols/methods/files/diagnostic-IDs, resolved
TODO/FIXME/HACK/"temporary"/"workaround for X", descriptions of old behavior, copy-paste comments describing a different member, dead-code comments. - Doc rot —
CLAUDE.md/README/CHANGELOG/ workflow tables whose dependency versions, file lists, command names, or workflow names don't match reality. (Shipped pastCHANGELOGentries are history, not rot — never flag them.) - Infra rot — workflow comments that lie; unpinned actions (
@v1→ SHA-pin with a# vNcomment); hardcoded publish accounts → dynamic secrets; expired/long-lived API keys → OIDC trusted publishing. - Version sync — pins/claims out of sync across
Version.props/Directory.Packages.props/global.json/ docs; published-vs-pinned drift; a property referenced but defined only by an injected SDK (annotate, don't "fix"). - Dependency rationalization — a narrow sub-package used where a parent/meta suffices; a superseded package still used after its successor shipped; redundant direct references already present transitively. This dimension needs external knowledge, not just the repo — see
references/dependency-rationalization.md.
Discipline — non-negotiable
- Correct beats delete. If a comment explains a genuinely non-obvious why (a workaround's reason, an invariant), fix the wrong details and KEEP the explanation. Delete only when purely obsolete.
- Verify root + every transitive use. Before changing anything a comment/doc describes, read the code it refers to and everything that depends on it. Never "fix" a comment to match a wrong assumption — fix whichever of {comment, code} is actually wrong, and chase the change through every caller.
- Never invent. Can't confirm it's stale? Leave it; report it as
unverified. Do not guess. - Terse + behavioral corrections. Say what/why; don't restate the code.
- No drive-by behavior changes. Comments/docs + the named CI modernizations only — unless fixing rot exposes a real bug, in which case say so and fix the root cause.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 44 lines · 133 tokens per session scan A ec2b5160c1d2
derot is a skill published in the GitHub repository ANcpLua/ancplua-claude-plugins (6 stars, last pushed 22d ago), licensed MIT. It adds 133 tokens to every session and 1,158 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.