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 ConnieHan2019/code-removal-skill --skill dead-code-removalgit clone --depth 1 https://github.com/ConnieHan2019/code-removal-skillWrote 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/conniehan2019/code-removal-skill/dead-code-removal)<a href="https://agentmods.dev/skills/conniehan2019/code-removal-skill/dead-code-removal"><img src="https://agentmods.dev/badge/skills/conniehan2019/code-removal-skill/dead-code-removal/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/conniehan2019/code-removal-skill/dead-code-removal"><img src="https://agentmods.dev/badge/skills/conniehan2019/code-removal-skill/dead-code-removal.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 | $0.00119 | $0.08068 |
| Opus 5.5 | $0.00048 | $0.03227 |
| Sonnet 5.5 | $0.00024 | $0.01614 |
| Haiku 4.5 | $0.00012 | $0.00807 |
Grade A, and why
dead-code-removal 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 1mo 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 — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dead Code Removal Skill
version: 0.1.0 status: open-source release (methodology mature; packaging new) language toolchain: Go (
scripts/*.sh); methodology is language-agnostic — swap the scripts to support another language.
🚨 Top-Level Non-Negotiable Rules (read first — violations cause repeated permission prompts)
If you run this skill inside a permission-gated agent (e.g. Claude Code), violating any of these forces a permission prompt on nearly every command.
-
Don't prefix the validation scripts with env vars
- ❌
GOCACHE=... GOFLAGS=-mod=mod scripts/build-check.sh ./... - ✅
scripts/build-check.sh ./... - Why: an env-var prefix creates a new command prefix that is not on your allowlist → a fresh prompt every time. If your environment needs fixed cache/proxy locations, export them once in your shell profile, or edit the script defaults — never prefix at the call site.
- ❌
-
Don't add decorative pipes (
| head,| tail,| tee)- ❌
scripts/build-check.sh ./... 2>&1 | tail -5 - ✅
scripts/build-check.sh ./...(output is short; if long, truncate with your editor/Readtooling) - Why: a composite command re-matches the allowlist;
tail/headmay not be allowed, so the whole pipeline prompts.
- ❌
-
Don't edit source code with Bash
- ❌
sed -i .../awk > tmp && mv tmp file/head -n X file > new && tail >> new && cp new file - ✅ Use your editor / file-edit tooling
- Why: Bash-edited source can't be diffed cleanly and easily trips sandbox write permissions.
- ❌
-
Don't dress up an unverified risk as a decision for the user
- Before escalating to a human, pass the 3 gates in §Supervisor Mode → Escalation Gate (fact closure / technical closure / decision residue).
If you violate 1–3, re-read this section and switch to the prescribed form — don't power through and trigger the prompt.
Goal
Given a deprecated entry point (HTTP handler) or a module directory, automatically find and remove every downstream dependency that is referenced only by the dead code — so the removal is both correct and complete in a single pass.
What ships with it
39 files 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.
- references/acceptance-criteria.md 9.6 KB
- references/acceptance-criteria.zh.md 8.3 KB
- references/agent-orchestration-workflow.md 19 KB
- references/agent-orchestration-workflow.zh.md 16 KB
- references/blind-review-prompt.md 3.9 KB
- references/blind-review-prompt.zh.md 3.3 KB
- references/blind-review-result-template.md 1.4 KB
- references/blind-review-result-template.zh.md 1.3 KB
- references/drafts/langgraph-implementation-design.md 11 KB
- references/drafts/langgraph-implementation-design.zh.md 11 KB
- references/drafts/permission-hook.md 6.5 KB
- references/drafts/permission-hook.zh.md 5.6 KB
- references/eval-checklist.md 9.3 KB
- references/eval-checklist.zh.md 8.0 KB
- references/execution-result-template.md 1.1 KB
- references/execution-result-template.zh.md 1.0 KB
- references/executor-prompt-template.md 2.6 KB
- references/executor-prompt-template.zh.md 2.3 KB
- references/iteration-template.md 2.2 KB
- references/iteration-template.zh.md 2.0 KB
- references/orchestration-proof-template.md 2.4 KB
- references/orchestration-proof-template.zh.md 2.3 KB
- references/permission-template.md 11 KB
- references/permission-template.zh.md 9.9 KB
- references/README.md 1.8 KB
- references/README.zh.md 1.6 KB
- references/removal-list-template.md 6.5 KB
- references/removal-list-template.zh.md 5.9 KB
- references/runtime-validation-checklist.md 6.8 KB
- references/runtime-validation-checklist.zh.md 5.8 KB
- references/supervisor-board-template.md 789 B
- references/supervisor-board-template.zh.md 674 B
- references/supervisor-checklist.md 6.5 KB
- references/supervisor-checklist.zh.md 5.3 KB
- scripts/build-check.sh 946 B runs code
- scripts/module-gone-check.sh 561 B runs code
- scripts/tidy-check.sh 933 B runs code
- scripts/vet-check.sh 771 B runs code
- SKILL.zh.md 30 KB
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.
- 1mo ago First seen · 629 lines · 119 tokens per session scan A 65aeb7a1cf11
dead-code-removal is a skill published in the GitHub repository ConnieHan2019/code-removal-skill (5 stars, last pushed 3mo ago), licensed MIT. It adds 119 tokens to every session and 8,068 once invoked, about $0.0005 per session on Opus 5.5. 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.
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…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.