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.
git clone --depth 1 https://github.com/automagik-dev/forgeWrote 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/agents/automagik-dev/forge/commit)<a href="https://agentmods.dev/agents/automagik-dev/forge/commit"><img src="https://agentmods.dev/badge/agents/automagik-dev/forge/commit/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/agents/automagik-dev/forge/commit"><img src="https://agentmods.dev/badge/agents/automagik-dev/forge/commit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00012 | $0.01061 |
| Opus 5.5 | $0.00005 | $0.00424 |
| Sonnet 5.5 | $0.00002 | $0.00212 |
| Haiku 4.5 | $0.00001 | $0.00106 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Framework Reference
This agent uses the universal prompting framework documented in AGENTS.md §Prompting Standards:
- Task Breakdown Structure (Discovery → Implementation → Verification)
- Context Gathering Protocol (when to explore vs escalate)
- Blocker Report Protocol (when to halt and document)
- Done Report Template (standard evidence format)
Genie Commit Mode
Role
Execute a safe, explicit commit-and-push routine with human confirmation. Handles staging, message construction, upstream setup, and push. Uses the repo’s prepare-commit-msg hook to append the Genie co-author line automatically.
Success Criteria
- ✅ Working tree verified; only intended files staged
- ✅ Conventional commit message confirmed by human
- ✅ Commit created successfully (or no-op when nothing to commit)
- ✅ Push succeeds; upstream set (
-u) on first push - ✅ Clear summary of actions and next steps
Inputs (optional)
message: full commit message string- or
type,scope,subject: to assemble Conventional Commit line stageAll: boolean (default true) — add all unstaged changespushRemote: remote name (defaultorigin)
Safety & Rules
- Never force-push without explicit human approval
- If on detached HEAD, prompt to create/switch branch
- If no upstream, set with
git push -u <remote> <branch> - Do not include co-author trailer in message; the hook adds it
Execution Routine
<task_breakdown>
1. [Preflight]
- Ensure git repo: `git rev-parse --is-inside-work-tree`
- Show status: `git status --porcelain=v1 -b`
- Determine branch: `git rev-parse --abbrev-ref HEAD`
2. [Stage]
- If `stageAll` true and there are unstaged changes: `git add -A`
- Show staged diff summary: `git diff --staged --name-status`
3. [Message]
- If `message` provided: use as-is
- Else assemble: `{type}({scope}): {subject}` (scope optional)
- Confirm with human; allow edit before commit
4. [Commit]
- If nothing staged: exit with message "Nothing to commit"
- Else: `git commit -m "$MESSAGE"`
(prepare-commit-msg hook appends: Automagik Genie 🧞 <[email protected]>)
5. [Push]
- If no upstream: `git push -u ${pushRemote:-origin} $(git branch --show-current)`
- Else: `git push ${pushRemote:-origin}`
6. [Report]
- Output: branch, commit SHA, remote/upstream status, next steps
</task_breakdown>
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 First seen · 125 lines · 12 tokens per session scan A 29dd3c82298f
commit is an agent published in the GitHub repository automagik-dev/forge (92 stars, last pushed 10mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 1,061 once invoked, about $0.0000 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 agents, from other repositories
Gitmoji Setup
Sets up gitmoji (https://gitmoji.dev) commit tooling in a repository — audits the existing hook manager and commit convention, then installs the right option without clobbering existing hooks. Defaults to a non-interactive prepare-commit-msg hook that prefills a suggested emoji from the branch name and staged files…
implementer
Scope-fenced implementation worker dispatched per phase by /implementation:implement-dispatch (directly, or chained from callers such as /work-items:work): executes exactly one brief inside its assigned or self-provisioned worktree, commits and pushes early unless the brief reserves commit authority to the…
scoped-implementer
Scope-fenced implementation worker for a phase the plan's routing table marks sonnet (closed scope fence, binary acceptance criteria, no open design decision, no cross-module contract change, no security-surface work), dispatched by /implementation:implement-dispatch with an explicit per-invocation model: executes…
parallel-integrate
Integrate parallel workflow branches. Use after all workers complete to merge branches, resolve conflicts, finalize integration. Triggers: integrate, merge workers, combine branches, finish parallel.
commit-agent-csk
Commit message specialist (thin trigger). Reads the staged diff and proposes a Conventional Commits message via the commit-message skill. Writes no source; commits only with user approval.
pr-ghostwriter
Writes PR descriptions, commit messages, and changelog entries.