Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tessaryai/plugins/plugin install crewWrote 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/tessaryai/plugins/spring-cleaning)<a href="https://agentmods.dev/skills/tessaryai/plugins/spring-cleaning"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/spring-cleaning/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/tessaryai/plugins/spring-cleaning"><img src="https://agentmods.dev/badge/skills/tessaryai/plugins/spring-cleaning.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 | $0.00069 | $0.00998 |
| Opus 5.5 | $0.00028 | $0.00399 |
| Sonnet 5.5 | $0.00014 | $0.00200 |
| Haiku 4.5 | $0.00007 | $0.00100 |
Grade A, and why
spring-cleaning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spring-cleaning
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run.
You perform bounded, evidence-backed cleanup. You never make sweeping rewrites — each cleanup is small, justified, and validated. Your ceiling is a review-ready PR — never merge.
Optional argument is the scope: dead-code, unused-deps, stale-todos, orphaned, or
all (default: ask the user, or dead-code if unattended).
0. Load config
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Obey guardrails.protected_paths (never touch these), commands.* (to validate), and
labels.{agent_pr,cleanup}.
Then read ${CLAUDE_PLUGIN_ROOT}/reference/work-model.md and resolve the mode before any
gh call. Detection and validation are identical in both modes; only the output differs
(step 4).
1. Detect (read-only first)
Pick detectors by language — use what the repo already has before installing anything:
- dead code / unused exports:
kniports-prune(JS/TS),ruff check --select F401vulture(Python),go vet/deadcode(Go),cargo +nightly udeps(Rust).
- unused dependencies:
depcheck(JS/TS), comparing manifest vs imports otherwise. - stale TODOs:
grep -rn "TODO\|FIXME\|XXX"and cross-reference withgit blameage. - orphaned files: files with no inbound references / not in any build graph.
Gather evidence for each candidate (e.g. "no inbound references", "import removed in PR #X"). Do not act on anything you can't justify.
2. Propose a bounded set
For the chosen scope, select the high-confidence, evidence-backed changes. Exclude
anything matching protected_paths. When unsure, leave it and note it in the PR description
as a candidate for human judgment.
If the cleanup is huge. If detection turns up far more justified cleanup than fits a single
bounded PR — it naturally breaks down module by module or across many categories — don't
silently truncate to the cap and don't sprawl. Add a decomposition plan to your report back
to the orchestrator: a numbered list of independent units (e.g. one per module or category),
each with description, target (the files/module it owns), primitive: spring-cleaning, and
any depends_on. Flag the report scale-out-recommended. The orchestrator decides whether
to fan it out, always confirming with the user first (see
${CLAUDE_PLUGIN_ROOT}/reference/scale-out.md for the unit shape). You only recommend — you
never spawn anything.
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 · 86 lines · 69 tokens per session scan A 6c7d47acb39c
spring-cleaning is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 998 once invoked, about $0.0003 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
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).
review
5-pass structured code review — correctness, security, performance, readability, consistency.