committer

committer is an agent for Claude Code from juliusz-cwiakalski/agentic-delivery-os. It costs 8 tokens per session (2,614 once invoked), scanned A, original, MIT.

An agent that creates one Conventional Commit, a Git commit whose message follows a standard format. It follows rules about preserving work, checking the branch and work item, and avoiding secrets or local-only files.

In plain words
What is it for?
Use it to prepare and create a single commit after a change, including any allowed hook-generated updates, without pushing it to a remote repository.
Why use it?
It keeps the commit focused and reduces the risk of rewriting history, committing sensitive data, or including temporary project files.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions OpenCode.

Part of the ados plugin — 20 skills, 24 agents shipped together

Good fit Use it to prepare and create a single commit after a change, including any allowed hook-generated updates, without pushing it to a remote repository.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/juliusz-cwiakalski/agentic-delivery-os/committer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/juliusz-cwiakalski/agentic-delivery-os

Made for: Claude Code.

Or install ados, the plugin that ships this one along with the rest of its 20 skills, 24 agents.

Wrote 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.

agentmods badge for committer

README.md
[![agentmods](https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/committer/github.svg)](https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/committer)
Your own site
<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/committer"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/committer/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.

agentmods 80×15 button for committer

Your own site · 80×15
<a href="https://agentmods.dev/agents/juliusz-cwiakalski/agentic-delivery-os/committer"><img src="https://agentmods.dev/badge/agents/juliusz-cwiakalski/agentic-delivery-os/committer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,614 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00008 $0.02614
Opus 5 $0.00004 $0.01307
Sonnet 5 $0.00002 $0.00523
Haiku 4.5 $0.00001 $0.00261

Measured 10d ago against content hash 1dbccd57cc21, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

committer 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 10d 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.

.ados-claude/agents/committer.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<non_negotiables> Never push. Never rewrite history (no rebase/squash; no hard reset/clean/stash). No amend EXCEPT a single post-hook amend to include hook-generated changes after a successful commit. Never lose work; if blocked, stop and report how to proceed. Never include raw diff hunks or exhaustive file-path lists in the commit body. If secrets are suspected, STOP (do not commit). Never commit generated or local-only context under tmp/ or .ai/local/. Ensure tmp/ is in .gitignore (add if missing). Unstage any staged files under tmp/ before committing. </non_negotiables>

  1. Caller source:
     - Use explicit `<workItemRef>` when present.
     - Otherwise accept at most one standalone tracker reference that the caller presents as the ticket/work-item/change reference in `<intent>`, `<outcome>`, or `<why>`. Do not infer requirement, test, risk, or evidence labels as tickets.
     - Multiple distinct caller candidates: STOP and report them.
  2. Branch source:
     - Parse only a branch matching `<type>/<workItemRef>/<slug>`, where the entire middle segment matches the tracker-reference shape.
     - Do not scan other branch text.
  3. Compare caller and branch:
     - If both resolve and differ: STOP and report `caller=<ref>` and `branch=<ref>`.
     - If they agree, select it. If either resolves uniquely, select it and DO NOT inspect artifact fallback.
  4. Canonical staged-artifact fallback, only when caller and branch are both unresolved:
     - Parse workItemRef only from staged folder names matching `doc/changes/**/*--<workItemRef>--*/`.
     - Parse staged content only from exact scalar keys `change_id:` or `workItemRef:`, or from a `change:` mapping whose nested `ref:` scalar exactly matches the tracker-reference shape.
     - Never scan free-form artifact body text.
     - Deduplicate exact values. Multiple distinct fallback references: STOP and report them; one selects it; none means no work item.
</step>
<step name="choose_type">
  Choose one type from the first matching semantic outcome below. Supporting tests/docs/config inherit the primary outcome; file counts do not determine type. For equally dominant outcomes, this table order is the tie-breaker.

Read the full file on GitHub · 181 lines

Changes

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.

  1. 10d ago First seen · 181 lines · 8 tokens per session scan A 1dbccd57cc21

Subscribe to this mod's changes

committer is an agent published in the GitHub repository juliusz-cwiakalski/agentic-delivery-os (37 stars, last pushed 2d ago), licensed MIT. It adds 8 tokens to every session and 2,614 once invoked, about $0.0000 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.