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 agentmods add skills/kkollsga/codingest/dev-docs-cleanupnpx skills add kkollsga/codingest --skill dev-docs-cleanupgit clone --depth 1 https://github.com/kkollsga/codingestWhat 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 | $0.00104 | $0.01624 |
| Opus 5 | $0.00052 | $0.00812 |
| Sonnet 5 | $0.00021 | $0.00325 |
| Haiku 4.5 | $0.00010 | $0.00162 |
Grade A, and why
dev-docs-cleanup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dev-docs cleanup
dev-docs/ accumulates project plans, intermediate files, and scratch (it's
gitignored working state). Over time it goes stale and cluttered. This skill
tidies it: nothing is hard-deleted from the durable set — stale files are
soft-deleted to dev-docs/bin/ with a 7-day grace, and any open actions are
preserved in an evergreen dev-docs/todos.md.
Layout is dev-docs/README.md (the canonical map). Durable dirs —
plans/, designs/, bench/scripts/, bench/results/, and todos.md — are
never auto-purged; only temp/, bench/out/, and bin/ are time-boxed.
1. Auto-purge generated dirs (always first)
At skill start, hard-delete the three time-boxed locations. Never touch
bench/scripts/ or bench/results/ — harnesses and the parity/perf result
history are durable; only bench/out/ (heavy built graphs/dumps) is disposable.
cd "$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
mkdir -p dev-docs/temp dev-docs/bin dev-docs/bench/out
find dev-docs/temp -type f -mmin +1440 -print -delete # ephemeral handoff, >1 day
find dev-docs/bench/out -type f -mtime +14 -print -delete # heavy built .kgl/stat dumps, >14 days
find dev-docs/bin -type f -mtime +7 -print -delete # soft-deleted docs, >7 days
The grace period starts at soft-deletion, not at last edit — mtime
survives a mv, so a doc last edited eight days ago would be hard-deleted the
moment it lands in bin/, silently bypassing its own grace (three docs went
that way on 2026-08-22). Every move into dev-docs/bin/ therefore gets a
touch:
mv <doc> dev-docs/bin/ && touch dev-docs/bin/<doc-basename>
Report what was purged (path list, or "nothing aged out"). Only bench/out/ is
purged from bench/ — the small csv/json regression record in bench/results/
is kept indefinitely.
2. Read todos.md — the only file read by default
todos.md is the index of open threads; its backlinks point to the durable docs
under plans/. Read only todos.md to start. Do NOT read through plans/,
and never read designs/ — design-reference docs aren't todos-driven
(they're durable reference, out of scope for cleanup). You open a specific doc
only when a check below points you at it (a misplaced file, or the backlink
behind a stale action) — never the whole folder. This keeps cleanup cheap: one
file read, plus at most the few docs the checks flag.
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.
- yesterday First seen · 113 lines · 104 tokens per session scan A 1ccbe0070e04
dev-docs-cleanup is a skill published in the GitHub repository kkollsga/codingest (0 stars, last pushed yesterday), licensed MIT. It adds 104 tokens to every session and 1,624 once invoked, about $0.0005 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…