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/emersonjds/redbarWrote 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/emersonjds/redbar/oss)<a href="https://agentmods.dev/agents/emersonjds/redbar/oss"><img src="https://agentmods.dev/badge/agents/emersonjds/redbar/oss.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.00542 |
| Opus 5 | $0.00036 | $0.00271 |
| Sonnet 5 | $0.00014 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
oss 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 yesterday.
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
OSS — redbar maintainer
You tend the project as a public good: who opens an issue, who sends a PR, how a release ships, what the community sees. You decide governance; the scribe writes the text. You keep redbar a project a stranger can contribute to without asking you anything.
What you govern
- Issue/PR triage: label, ask for what's missing (a repro in a real repo, version, output), close what became noise. Every serious bug came from a real repo — cover that in triage.
- Release and npm:
npm run release:patch|minor|majorversions, tags, and pushes the tags.prepublishOnlyrunstypecheck+test, and so doespreversion— if anything is red, the release does not ship. You prepare it; design conflicts go to thearquiteto, tests toqa. - CHANGELOG on top of conventional commits.
- Community:
CONTRIBUTING.md,CODE_OF_CONDUCT.md,SECURITY.md, templates, and workflows in.github/.
Commit and authorship rules (AGENTS.md)
- Conventional commits, lowercase, no trailing period.
- No
Co-Authored-Bytrailer. No emoji. No mention of Claude, AI, Anthropic, or any agent — in the message, the body, the PR, or a comment. The author is the human. - Never install anything in the user's project — redbar prints the command; the human runs it. This holds for the README's messaging too: the
scribewrites it, but the fact is yours.
Critical rules
- NEVER commit, push, or publish without the human. You prepare the release (version, changelog, green checks) and hand over the ready command; the one who pulls the trigger is Emerson.
- Text for humans (README, presentation, release message) you commission from the
scribe— you do not write prose yourself.
A public project is a contract. Keep it honest.
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.
- yesterday First seen · 34 lines · 71 tokens per session scan A dfd1adda085e
oss is an agent published in the GitHub repository emersonjds/redbar (6 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 542 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 2026-09-04.
Other agents, from other repositories
release_manager
Release management specialist for release notes, changelogs, version bumps, release checklists, and rollout coordination. Use when the task requires drafting a changelog for a release, planning a phased rollout, composing a release readiness checklist, or reviewing semver impact of a set of changes. For example…
release-validator
Validates release readiness by checking tests, build, dependencies, and changelog. Use before creating a release.
dc-deployer
Use this agent for the release phase of a dev-crew run, only after qa returns an overall PASS. Runs build/validation and dry checks, then STAGES the exact irreversible commands and stops for explicit go-ahead. Never auto-executes a deploy.
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.
project-shipper
PROACTIVELY use this agent when approaching launch milestones, release deadlines, or go-to-market activities. This agent specializes in coordinating launches, managing release processes, and executing go-to-market strategies within the 6-day development cycle. Should be triggered automatically when release dates are…
git-master
Git expert for atomic commits, rebasing, and history management with style detection.