Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/gtapps/claude-code-hermitnpx agentmods add skills/gtapps/claude-code-hermit/stale-proposalsWrote 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/gtapps/claude-code-hermit/stale-proposals)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/stale-proposals"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/stale-proposals/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/gtapps/claude-code-hermit/stale-proposals"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/stale-proposals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 94 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00140 | $0.01676 |
| Opus 5.5 | $0.00056 | $0.00670 |
| Sonnet 5.5 | $0.00028 | $0.00335 |
| Haiku 4.5 | $0.00014 | $0.00168 |
Grade A, and why
stale-proposals 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- stale-proposals — 98% identical, 10 lines differ
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stale Proposals
Reconcile the open proposal queue against what actually shipped.
Trust shipping evidence more than age. An unambiguous shipped match can close automatically because the evidence is inspectable and the decision is reversible. Age or silence alone requires the user's judgment.
Invocation
$stale-proposals— audit the queue, auto-resolve strong shipped matches, and ask about everything else.$stale-proposalswithno applyorreport only— write nothing and report all verdicts.
Step 1 — Collect bounded evidence
From the repository root, run:
bun .agents/skills/stale-proposals/scripts/collect-evidence.ts
The script prints one of:
OK|<bundle-path>|<open>|<bullets>|<commits>|<cutoff>NONE|no-open-proposalsNONE|no-proposals-dir
For NONE|no-open-proposals, report Queue is clean — no open proposals. and stop. For a missing proposals directory, report the missing queue and stop.
Do not read the evidence bundle in the main session. It can be tens of thousands of tokens and exists specifically to keep that corpus isolated.
Step 2 — Match in one isolated worker
Spawn one worker agent with a fresh context (fork_turns: "none" when supported). Give it only the repository root, evidence-bundle path, and the contract below. Wait for its result before continuing. If agent spawning is unavailable, stop and explain that this audit requires one isolated worker; do not load the bundle into the main session as a fallback.
Use this contract verbatim, substituting the real path:
Read the evidence bundle at
<path>. It lists open proposals, then CHANGELOG bullets, then first-parent commits.For each open proposal, decide whether the thing it asked for has already shipped. Emit exactly one line per proposal, and nothing else:
SHIPPED-STRONG|<PROP-ID>|<plugin> <version> / <commit or "changelog">|<one sentence: what the evidence says, in the changelog's own words>SHIPPED-WEAK|<PROP-ID>|<evidence ref>|<one sentence: what matches and what you could not confirm>AGED|<PROP-ID>|<age in days>|<one sentence: why nothing has moved on this>OPEN|<PROP-ID>STRONG requires all three: the evidence names the same component the proposal targets; it describes the same behavior change the proposal asked for; and no distinct part of the proposal's ask is left unaddressed. A proposal asking for three things where the changelog delivers two is WEAK, not strong — partial delivery is the single most likely way this audit closes live work by mistake, so when you notice yourself arguing for why a gap "probably doesn't matter," that is WEAK.
Ignore date order at your peril: evidence dated before a proposal was created cannot be that proposal shipping. It is usually the prior art the proposal was written against. Changelog dates have day granularity while proposals carry a timestamp, so same-day evidence cannot be ordered at all — treat it as at most
SHIPPED-WEAKand say so.A proposal can ship under a different name than it asked for. Match on substance — the component, the behavior, the problem being closed — not on the proposal's chosen identifier.
Use
AGEDonly when there is no shipping evidence at all AND no commit in the history touches the proposal's subject area since it was created — an untouched subject is what "inert" actually means. Age alone is not staleness; a good idea nobody got to yet isOPEN.Be conservative.
OPENis the correct answer for most proposals and costs nothing; a wrongSHIPPED-STRONGsilently closes live work.
What ships with it
2 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.
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 Changed a9c1bc50b10c
- 1mo ago First seen · 122 lines · 140 tokens per session scan A 3805f237669f
stale-proposals is a skill published in the GitHub repository gtapps/claude-code-hermit (82 stars, last pushed yesterday), licensed MIT. It adds 140 tokens to every session and 1,676 once invoked, about $0.0006 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 skills, from other repositories
pave-catalog
Build a service catalog — schema, starter entries, and governance model. Produces what information to capture per service, how it's maintained, and where it lives. Use when asked to "service catalog", "what services do we have", "catalog our services", "service inventory", or "who owns what".
atlas-present
Generate a polished HTML presentation page and Obsidian Canvas for big releases — new products, takeovers, major migrations. Non-technical audience. Use when asked to "present this", "release announcement", "show what we built", or "stakeholder update".
crest-narrative
Strategic narrative — write a standalone strategy memo that frames product direction, bets, and rationale for a planning horizon. Use when asked to "write a strategy doc", "product vision", "strategic narrative", "company strategy memo", "planning memo", or "explain our product direction".
crest-okr
OKR design — create objectives and key results with a North Star metric, input metrics tree, and cadence. Use when asked to "set OKRs", "define our objectives", "what should we measure this quarter", "design our OKR framework", "build a metrics tree", or "what's our North Star".
apex-recon
Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project", "orient me on this codebase", "what's the state of the repo", "what's in progress", or before starting work on an unfamiliar codebase.
crest-recon
Strategic context reconnaissance — read existing roadmaps, OKRs, competitive docs, and briefs to establish context before planning. Use when asked to "understand our strategy", "what's the current roadmap", "what OKRs do we have", "strategic context", or before starting any prioritization or roadmap work.