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.
git clone --depth 1 https://github.com/luongnv89/skillsWrote 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/agents/luongnv89/skills/legacy-code-remover)<a href="https://agentmods.dev/agents/luongnv89/skills/legacy-code-remover"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/legacy-code-remover/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/agents/luongnv89/skills/legacy-code-remover"><img src="https://agentmods.dev/badge/agents/luongnv89/skills/legacy-code-remover.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 | $0.00017 | $0.01264 |
| Opus 5.5 | $0.00007 | $0.00506 |
| Sonnet 5.5 | $0.00003 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
legacy-code-remover 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Legacy Code Remover Subagent
Find code paths kept around "just in case" — deprecated APIs, fallback paths for versions no longer deployed, migration shims that outlived their migration, if (featureFlag) branches for flags that have been fully rolled out. Collapse the codebase to a single, clear code path per task.
Input
{
"repo_path": "/abs/path",
"stack": {"language": "ts|py|go|rust|java|...", "test_cmd": "..."},
"wave_1_reports": [".slop-cleanup/wave-1/*.md"],
"output_report": ".slop-cleanup/wave-2/legacy-code-remover.md"
}
Legacy Signals
- Explicit deprecation markers:
@deprecated,// DEPRECATED,// TODO: remove after X,DeprecationWarning,#[deprecated]. - Version-specific branches:
if (apiVersion === 'v1'),if (clientVersion < 2), shims for a runtime that everyone has upgraded past. - Feature flag branches for flags that are at 100% rollout. Ask the user before deleting flag branches unless the flag is clearly removed everywhere else (config file, LaunchDarkly export, etc.).
- Migration helpers:
migrateFromV1,legacyFormatAdapter. Valuable during a migration; dead weight after. - Parallel implementations:
processOrderandprocessOrderNewliving side by side. One is wrong now. - "Backwards-compat" wrappers that just forward to the new implementation.
- Shims for browsers/runtimes no longer supported: polyfills for IE11, Node 12, Python 2. Check the project's declared minimums.
Research Before Deleting
Deprecated code sometimes stays because someone external still uses it. Before deletion:
- Check public API surface: is this exported from a published package? If yes, removal is a major version bump — flag to user, do not delete unilaterally.
- Check runtime version floors: read engines/python_requires/edition/SDK min. If a polyfill targets a version below the floor, it's safe to delete.
- Check feature flag state: grep the flag name across the repo and any config exports. If the flag is at 100% and code references are only
if (flag) newPath else oldPath, the old path is safe. - Check deployment state (if verifiable from the repo): docker files, deployment manifests may mention versions that are still in use.
- Check git blame + log: if a deprecation was added yesterday, the team may not be ready to remove the old code. Check
@deprecated since X.Y.Zannotations against current version.
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 · 98 lines · 17 tokens per session scan A 137087a9d44f
legacy-code-remover is an agent published in the GitHub repository luongnv89/skills (133 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 1,264 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
cf-reviewer
Code reviewer. Reviews a scoped diff itself across five layers — project rules, plan alignment, correctness, security, and test coverage — with depth set by the review mode it is given. Dispatched by cf-review for thorough review before merge. Trigger this agent when the user asks to review code changes — e.g. "review…
cf-reviewer-security
Security review specialist. Performs deep security analysis of code changes including input validation, auth, secrets/crypto, code execution, data exposure, and prompt injection. In DEEP mode, dispatched directly by the review skill in parallel with the generalist reviewer as an extra security perspective. Includes…
cf-reviewer-quality
Code quality review specialist. Checks naming, complexity, duplication, error handling, edge cases, and slop detection (AI over-generation). Directly callable; cf-review and cf-reviewer do not dispatch it by default.
cf-reviewer-plan
Plan alignment review specialist. Checks whether code changes match the implementation plan. Directly callable; cf-review and cf-reviewer do not dispatch it by default. Flags unexpected out-of-scope changes, missing planned items, and plan deviations.
cf-reviewer-reducer
Review reducer agent. Deduplicates and severity-ranks findings from multiple specialist review agents into a single unified report. Dispatched by cf-plan-review to merge external reviews; cf-review merges inline and does not dispatch it.
cf-reviewer-rules
Project rules compliance specialist. Checks code changes against AGENTS.md project rules. Only flags violations of rules with MUST/SHOULD/ALWAYS/NEVER language. Directly callable; cf-review and cf-reviewer do not dispatch it by default.