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/gtapps/claude-code-hermit/proposal-listnpx skills add gtapps/claude-code-hermit --skill proposal-listgit clone --depth 1 https://github.com/gtapps/claude-code-hermitWrote 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/proposal-list)<a href="https://agentmods.dev/skills/gtapps/claude-code-hermit/proposal-list"><img src="https://agentmods.dev/badge/skills/gtapps/claude-code-hermit/proposal-list.svg" alt="Measured on agentmods" 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 | $0.00045 | $0.01383 |
| Opus 5 | $0.00023 | $0.00691 |
| Sonnet 5 | $0.00009 | $0.00277 |
| Haiku 4.5 | $0.00005 | $0.00138 |
Grade A, and why
proposal-list 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 3d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proposal List
Lists all proposals with status, source, and age. Auto-detected proposals (from the learning loop) are listed first.
Step 0 — Channel reply
If this skill was invoked from a channel-arrived message (the inbound prompt contains a <channel source="..."> tag), reply via that channel's reply tool and render as Suggestion cards (§4a) instead of the table (§4). Otherwise emit the table to conversation as usual.
Plan
1. Read the proposals index
Read .claude-code-hermit/state/proposals-index.json — a derived cache of every proposal's frontmatter (id, status, source, category, title, created, session, responded, plus an unparseable flag), refreshed on every proposal write by the generate-summary PostToolUse hook. (fresh read — re-read the file now; do not reuse a value cached in context from before compaction.)
Rebuild the index first, then read it:
bun ${CLAUDE_PLUGIN_ROOT}/scripts/proposal.ts index .claude-code-hermit
The rebuild reads frontmatter off disk — idempotent, no LLM/token cost — so run it unconditionally rather than trusting an mtime heuristic: it also catches out-of-band proposal writes and deletions that the generate-summary hook (which fires only on Edit/Write tool payloads) never sees. The script prints SKIP|no proposals dir when there are no proposals — in that case respond "No proposals found." and stop. If the index's count is 0, also respond "No proposals found." and stop.
Do not read proposal bodies. Every field the table needs is in the index row; this is the whole point of the index (reading a dozen full bodies costs ~22K tokens for a table that needs only frontmatter). Read a specific body only if the operator asks to see one proposal's detail.
2. (metadata is already parsed)
The index rows are the parsed metadata — use them directly. A file whose frontmatter can't be read (unreadable, or no --- block) appears with unparseable: true and every field null, counting as status unknown — the lifecycle can't act on it, since proposal.ts only writes frontmatter.
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.
- 3d ago First seen · 91 lines · 45 tokens per session scan A 511b6dc26816
proposal-list is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed yesterday), licensed MIT. It adds 45 tokens to every session and 1,383 once invoked, about $0.0002 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
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…