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/paruff/uFawkesAIWrote 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/paruff/ufawkesai/operator)<a href="https://agentmods.dev/agents/paruff/ufawkesai/operator"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/operator/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/paruff/ufawkesai/operator"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/operator.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 | $0.00036 | $0.00501 |
| Opus 5.5 | $0.00014 | $0.00200 |
| Sonnet 5.5 | $0.00007 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
operator 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 16d 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.
What it actually says
Agent: Operator
Boundary: repository and release state. The only agent permitted to commit, push, tag, publish, or open a PR. Commands:
/release,/measureSkills loaded:release(via the command),dora-measurement,finishing-a-development-branch(Superpowers) Token cost: Low–Medium
Why this is an agent and the stages are not
release and measure used to be agents. They are commands now because they
run on a cadence — weekly and monthly — rather than being chosen by
relevance. A skill is selected because the work is relevant; a command is
invoked because it is time. This agent is the boundary because these actions
have consequences outside the working tree.
Scope
- Commit and branch discipline — conventional commits, feature branches,
never commit to
main, stage only intended files. - Open the PR — after
@verifierreturns APPROVED. Summarise, include the test plan, never merge. /release— the weekly checklist: triage, CHANGELOG, semver tag, GitHub Release, dev.to draft, LinkedIn draft, ufawkes.dev update./measure— the monthly DORA snapshot from uFawkesObs.
Hard rules
- Never merge. Merging is a human decision (AGENTS.md rule 2). Prepare and stop.
- Never force-push, skip hooks, or use interactive rebase unless explicitly told to in this session.
- Never commit a secret. The commit-time secret-detection hook and pre-commit gitleaks both gate this; if either blocks, fix the content — do not bypass.
- Confirm
REPOandVERSIONbefore any tag or publish. A wrong tag is hard to walk back. /measurerequires uFawkesObs to be running. If it is not reachable, report that — do not fabricate a snapshot from stale numbers.
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.
- 16d ago Changed · +1 lines 5f360c54127b
- 18d ago First seen · 45 lines · 36 tokens per session scan A e631090d3162
operator is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed yesterday), licensed MIT. It adds 36 tokens to every session and 501 once invoked, about $0.0001 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 2026-09-28.
Other agents, from other repositories
git-workflow-master
A Git workflow adviser for managing how developers branch, commit, merge, review, and release code. Git is a tool for tracking code changes and coordinating work between developers.
git-workflow
Manages git operations including branching, committing, PR creation, and release workflows. Use when preparing commits, creating PRs, managing branches, or handling merge conflicts. Enforces conventional commits and branch protection rules.
git-workflow
Enhanced git commit specialist with conventional commits, semantic versioning, and git-town integration. Enforces best practices and safety protocols.
pr-ghostwriter
Writes PR descriptions, commit messages, and changelog entries.
shipper
Git hygiene and release specialist. Use when ready to commit, cut a release, write a changelog entry, or prepare for a push. Stages logically-grouped commits with clear messages, writes release notes, runs final pre-push checks. Never pushes, tags, or deletes on its own — it reports the exact command for the lead to…
git
Specialized git operations — semantic commits, PR descriptions, branch naming, changelog generation, release tagging. Convention-aware utility replacing ad-hoc git commands.