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-createnpx skills add gtapps/claude-code-hermit --skill proposal-creategit clone --depth 1 https://github.com/gtapps/claude-code-hermitWhat 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 | $0.00036 | $0.03003 |
| Opus 5 | $0.00018 | $0.01502 |
| Sonnet 5 | $0.00007 | $0.00601 |
| Haiku 4.5 | $0.00004 | $0.00300 |
Grade A, and why
proposal-create 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 today.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Proposal
Create a proposal only when you discover something with real leverage:
- A missing helper or utility that would save significant time across sessions
- A missing validation or guardrail that could prevent real errors
- A workflow improvement that would benefit multiple sessions
- A reusable pattern worth operationalizing
Three-Condition Rule
Only create a proposal if all three are true:
- Repeated pattern — observed more than once, across sessions. Skip for
scheduled-check/*,operator-request,current-session, andcapability-brainstormevidence sources — recurrence is either established by the check's own analysis, validated upstream byreflection-judge, or established by the brainstorm pass. For candidates whoseArtifact:line citesstate/observations.jsonl, the ledger graduation is the recurrence evidence — the judge verified the ledger; do not re-check here. For efficiency/cost-class candidates, evidence citing a machine-written state file with the measured values also counts — the judge verifies the file. Procedure-capture candidates meeting the ephemerality exception (ephemeral artifacts + quantified cost, single current session) also count — see reflect § Procedure capture. - Meaningful consequence — something goes wrong without fixing it
- Operator-actionable change — something the operator can concretely approve
If any applicable condition cannot be stated concretely, do not create the proposal. Respond: "Not enough evidence yet. Note it in SHELL.md Findings and revisit after more sessions."
Pre-Creation Gate
Before creating the proposal, call claude-code-hermit:proposal-triage. Pass Evidence Source: and Evidence Origin: when known:
Title: <proposal title>
Evidence Source: <archived-session | current-session | scheduled-check/<id> | operator-request | capability-brainstorm>
Evidence Origin: <own-work | external-content>
Evidence: <one-paragraph evidence summary>
Evidence Source: is optional (default: archived-session). Evidence Origin: is optional (default: own-work).
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.
- today Changed 88b5978bf046
- 2d ago First seen · 170 lines · 36 tokens per session scan A 1b5d464109cd
proposal-create is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 3,003 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.