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/qwerfunch/cladding/changelognpx skills add qwerfunch/cladding --skill changeloggit clone --depth 1 https://github.com/qwerfunch/claddingWhat 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 | $0.00121 | $0.00704 |
| Opus 5 | $0.00060 | $0.00352 |
| Sonnet 5 | $0.00024 | $0.00141 |
| Haiku 4.5 | $0.00012 | $0.00070 |
Grade A, and why
changelog 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cladding changelog — release notes from the spec
The spec is the SSoT, so "what shipped?" is collected, never recalled. clad changelog turns
<since>..HEAD into a deterministic manifest: feature shards classified (added-as-done /
flipped-to-done / modified-while-done / archived), grouped by capability (plus an
uncategorized bucket — itself a drift signal), the spec inventory diff, and conventional
feat:/fix: commits that name no feature id (work that shipped outside the spec — report it
honestly, don't hide it).
Protocol
- Collect. Run
clad changelog --json --since <ref>(omit--sinceto use the latest tag; if the repo has no tags the command says so — ask the user for a ref). - Render EN + KO release notes from the manifest, in the CHANGELOG.md house style:
- Open with a
**In one line:**abstract (what a user gains, one breath). - Group by the manifest's capability groups; use user-impact verbs ("the gate now runs your entry point"), not implementation verbs ("refactored stage runner").
- No
F-…/AC-…ids in prose (Soft Shell policy) — ids belong to the audit surface only. - Source every claim from the manifest — a feature
titleor anacceptance[]sentence. Never invent a change, never embellish beyond what an AC states. If the manifest is empty, say "no shipped changes since " — that line is the honest deliverable. - Put
unsharded_commitsunder an "Also changed" section, marked as not yet spec-tracked.
- Open with a
- Audit asks ("show verification", "어디까지 검증됐어?") → print
clad changelog --audit --since <ref>verbatim — that table keeps ids and marks every verification ref resolved ✓ / unresolved ✗ (a ✗ is spec-annotation drift worth reporting). - Catalog asks ("what does this project do, in full?") →
clad changelog --catalogprints the whole capability → feature → acceptance listing of the living spec.
clad changelog # markdown since the latest tag (deterministic fallback)
clad changelog --json --since v0.5.2 # the manifest you render notes from
clad changelog --audit --since v0.5.2
clad changelog --catalog
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 · 39 lines · 121 tokens per session scan A 520ee59cdbbd
changelog is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 704 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
map-plan
ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.
map-review
Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.
map-debug
Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…
map-learn
Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.
map-efficient
State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.
map-task
Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.