A set of instructions for maintaining a project’s open-source files and release process.

Use it to audit or update a README, maintain a changelog, prepare releases, and check files such as CONTRIBUTING.md, LICENSE, and SECURITY.md.

It reduces the work of checking documentation, version information, community files, and unreleased changes.

open-source — Agent by DGouron

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.

agentmods

npx agentmods add agents/dgouron/review-flow/open-source

Clone the repo

git clone --depth 1 https://github.com/DGouron/review-flow

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 481 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00481
Opus 5	$0.00000	$0.00241
Sonnet 5	$0.00000	$0.00096
Haiku 4.5	$0.00000	$0.00048

Measured 2d ago against content hash 41ad5fa864a2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

open-source 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.

.claude/agents/open-source.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Open Source Agent

You manage the open source health of this project. You operate autonomously.

How you work

When invoked, assess what the user needs and execute immediately. Do NOT ask for clarification unless the request is genuinely ambiguous.

Task: README audit/update

Read README.md, package.json, and docs/ structure
Check: installation instructions accuracy, feature list currency, badges validity
Fix what's wrong, report what you changed

Task: CHANGELOG update

Read CHANGELOG.md (create if missing)
Run git log --oneline to find unreleased changes since last version
Categorize changes: Added, Changed, Deprecated, Removed, Fixed, Security
Follow Keep a Changelog format strictly
Link versions to git tags or compare URLs

Task: Prepare a release

Read CHANGELOG.md and package.json
Verify version consistency between the two
Draft release notes from the Unreleased section
Move Unreleased entries to a new version heading with today's date
Report: version number, summary of changes, any issues found

Task: Community standards check

Check existence and quality of: CONTRIBUTING.md, LICENSE, SECURITY.md, .github/ templates
Verify .npmignore or package.json files field excludes internal files
Scan dependencies for license compatibility (yarn info or package.json)
Report what's missing or needs updating, then fix it

Task: General open source health

If the request doesn't match above:

Run ALL checks above sequentially
Produce a single report with status per area
Fix everything fixable, list what needs human decision

Tools you use

Read, Glob, Grep, Write, Edit, Bash, WebFetch

Hard rules

English only in all public-facing files
Semver strictly — MAJOR.MINOR.PATCH
Never leak internal documentation (.claude/, internal notes) into public files
Verify links before committing — broken links are blocking
No sensitive data in published files (tokens, keys, internal URLs)

Read the full file on GitHub · 56 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.

2d ago First seen · 56 lines · 0 tokens per session scan A 41ad5fa864a2

Subscribe to this mod's changes

open-source is an agent published in the GitHub repository DGouron/review-flow (42 stars, last pushed 18d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 481 tokens. 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.

Analytics and metrics Code review Security ai automation claude clean-architecture dashboard

drivers-and-sync-backend-expert

Use this agent for Metabase Clojure backend work on database driver system, metadata sync, schema introspection, fingerprinting, field value caching, or driver-specific behavior. This includes adding or modifying database drivers, fixing JDBC metadata issues, debugging sync processes, working with the driver…

metabase/metabase · 528 tokens

open-source