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/grimoire-rs/grimoire/commitnpx skills add grimoire-rs/grimoire --skill commitgit clone --depth 1 https://github.com/grimoire-rs/grimoireWhat 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 | $0.00067 | $0.02358 |
| Opus 5 | $0.00034 | $0.01179 |
| Sonnet 5 | $0.00013 | $0.00472 |
| Haiku 4.5 | $0.00007 | $0.00236 |
Grade A, and why
commit 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/commit — Working-Phase Commit Workflow
Commit working tree during active dev on feature/worktree branch. Working phase half of Grimoire two-phase branch workflow — rebasing-phase cleanup for main lives in /finalize.
See workflow-git.md for full model: branching rules, two-phase model, Checkpoint convention, land-ready definition. Skill assumes those, implements working-phase posture on top.
Working-Phase Posture
- Minimise commit count. Bundle freely. Amend rolling Checkpoints.
- One concern per commit relaxed. Honest bundle message (
chore(claude): bundle skill + rule + agent tweaks) beats fake one-concern narrative./finalizesplit/reword later. - Don't badger user about splitting. Worktree branches (
goat,evelynn,sion,soraka) explicitly working-phase by default. Cleanup at finalize time.
For land-ready branch contract, see "Land-Ready Definition" in workflow-git.md. That /finalize job, not /commit.
Inputs
Optional free-text arg. Treat as intent hint (e.g., fix grimoire install symlink bug), not full message — still draft final message. Flags:
/commit --amend— explicitly amend HEAD (bypasses Checkpoint-only safeguard)/commit --pr— force PR-branch prompt even if previously declined/commit --no-pr— skip + record PR skip
For rebasing-phase cleanup (squash, reword, split main..HEAD), use /finalize instead.
Workflow
1. Snapshot state (parallel batch)
git status --porcelain=v1(never-uall)git diff --stagedandgit diff --statgit log -5 --oneline— recent commits + scan for strandedCheckpointin windowgit rev-parse --abbrev-ref HEAD— current branchgit rev-list --count main..HEAD 2>/dev/null— commits ahead of maingit config --get branch.<current>.grim-skip-pr-prompt— PR prompt already answered?git log -1 --pretty=%s— HEAD itself Checkpoint?gh pr view --json number,state 2>/dev/null— open PR for branch?
What ships with it
1 file 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.
- 2d ago First seen · 162 lines · 67 tokens per session scan A a7ae8db3ea3e
commit is a skill published in the GitHub repository grimoire-rs/grimoire (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 67 tokens to every session and 2,358 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
agent-code-analyzer
Agent skill for code-analyzer - invoke with $agent-code-analyzer.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
haiku
When writing a haiku for this bot, follow these conventions.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
azure-mgmt-botservice-dotnet
Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.