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/dev-prnpx skills add gtapps/claude-code-hermit --skill dev-prgit 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 | $0.00074 | $0.04803 |
| Opus 5 | $0.00037 | $0.02402 |
| Sonnet 5 | $0.00015 | $0.00961 |
| Haiku 4.5 | $0.00007 | $0.00480 |
Grade A, and why
dev-pr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/dev-pr
Push the current branch and open a PR with a structured body. Reads commit history, the test results you just ran (per state-templates/CLAUDE-APPEND.md §Implementation Flow), any screenshots in raw/screenshots/, and an optional project PR template — assembles them into title + body — then calls the forge-appropriate CLI.
Configuration
commands.pr_create — the shell command used to open the PR. Set by /claude-code-dev-hermit:hatch from the detected forge. If unset, Gate 0 refuses immediately with a pointer to run /hatch.
- GitHub:
gh pr create— flags:--body-file <path>,--base <branch>. - GitLab:
glab mr create— flags:--description "$(cat <path>)",--target-branch <branch>. - Bitbucket / custom / other: operator-supplied. Gate 3 passes
--title "$TITLE" --body-file "$PR_BODY_TMP" --base "$BASE"to custom commands — wrap your CLI in a script that accepts those flags if the native CLI uses different ones.
The command must print the PR URL on a line matching ^https?://.
Prerequisites
- Verify
.claude-code-hermit/sessions/exists. If not: tell the operator to run/claude-code-hermit:hatchand/claude-code-dev-hermit:hatchfirst. - Read
.claude-code-hermit/config.jsononce. Cacheclaude-code-dev-hermit.protected_branches(defaults to["main", "master"]),commands.pr_create(no default — if unset, Gate 0 fails with a pointer to run/claude-code-dev-hermit:hatch),pr_base_branch,pr_template_path.
Argument
Optional --cwd <path>. When set, the entire flow targets the nested git repo at <path> end-to-end: Gate 0 checks (forge, branch, clean tree, tests, commits-ahead), Gate 1 push, Gate 2 title/body assembly, and Gate 3 commands.pr_create invocation all run against <path>. The PR opens against <path>'s remote, not the parent's — that's intentional (the child repo is the unit being PR'd) but the operator must understand it. Use this for nested-repo workflows (see CLAUDE-APPEND §Implementation Flow).
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.
- 2d ago First seen · 297 lines · 74 tokens per session scan A 9f80065057e1
dev-pr is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 74 tokens to every session and 4,803 once invoked, about $0.0004 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.
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…
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.
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.