Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bengous/claude-code-plugins/plugin install github-flowWrote 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/skills/bengous/claude-code-plugins/pr)<a href="https://agentmods.dev/skills/bengous/claude-code-plugins/pr"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pr/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/skills/bengous/claude-code-plugins/pr"><img src="https://agentmods.dev/badge/skills/bengous/claude-code-plugins/pr.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 | $0.00084 | $0.03888 |
| Opus 5.5 | $0.00034 | $0.01555 |
| Sonnet 5.5 | $0.00017 | $0.00778 |
| Haiku 4.5 | $0.00008 | $0.00389 |
Grade A, and why
pr 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 7d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR
Agents review the PR first. The body is for the human who opens it afterwards and wants the essential at a glance: what changed shape, what was checked, what was decided, and what is left open. Not a wall of text, not every file. The body shows the change, then says only what a picture cannot. Every view is text, so an agent reads the same facts.
Input
$ARGUMENTS
--dry-run: no push, no publish; print the title, the base, the body and the attachments instead.- Paths ending in
.png,.jpg,.gif,.mp4,.mov: files to attach. Alt text may follow the path after#. - The rest: what the reviewer should know, kept as facts in the body.
- Empty: everything comes from the branch.
Protocol
- Branch.
git branch --show-current. Ondev,main, the repo's default branch, or no branch: stop, showgit status --short, ask for a branch name; with no user to ask, reportno branchand stop. Uncommitted changes: stop and say so; the commit comes first (/git:commit). - Base.
devwhenorigin/devexists, elsegh repo view --json defaultBranchRef.ghtakes that bare name; agitcommand or the script takesorigin/<base>, since a local branch of that name may be missing or stale. - Evidence. Read before citing.
git log --oneline origin/<base>..HEADandgit diff --stat origin/<base>...HEAD: the size, the files.- Tests added by the branch:
git diff --stat origin/<base>...HEAD -- '*test*'. - The issue:
Closes #Nin a commit body, else the leading number of the branch name, else none.gh issue view <n> --json title,bodywhen there is one. - When the issue has an Out of scope section: every file of
git diff --name-only origin/<base>...HEADthat it names. - The repo's
.claude/github-flow.json: thevalidatecommands, and theverdictandtiercommands of steps 8 and 9. Without the file, the validation commands of itsAGENTS.mdorCLAUDE.md. ItsGLOSSARY.mdorCONTEXT.mdwhen one exists: the words that name the nodes of a view. - What ran this session, with its numbers.
- Views. Pick the smallest view that makes the key point clear, from the table under Views. A standard change gets one; a large one gets one per concern, three at most, a Before/After pair counting as one. Past three, Left open names the views left out.
- Moved, added or deleted directories:
${CLAUDE_PLUGIN_ROOT}/scripts/tree-diff.ts origin/<base>prints the tree diff. A directory moved, added or deleted whole is one line, and a directory where more than three files changed, all of them only modified, is a count. Keep the lines the reader needs and comment each one with what it owns now. - A Mermaid diagram: read
references/mermaid.mdfirst. GitHub's renderer has traps a terminal never shows. - Worked examples of every view:
references/views.md.
- Moved, added or deleted directories:
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago Changed fe124fd7a7dc
- 10d ago Changed · +15 lines · +14 tokens per session 242192b94ac2
- 1mo ago Changed · +29 lines · +19 tokens per session a2c0a1a952f6
- 1mo ago Changed · +2 lines 62d1f983157e
- 1mo ago Changed · +8 lines 1a248cf29f67
- 2mo ago First seen · 76 lines · 51 tokens per session scan A 7467e0cc6027
pr is a skill published in the GitHub repository bengous/claude-code-plugins (6 stars, last pushed yesterday), licensed MIT. It adds 84 tokens to every session and 3,888 once invoked, about $0.0003 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 2026-09-11.
pr compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| prbengous/claude-code-plugins | Skill | 6 | yesterday | MIT | A | 84 | Claude Code |
| flow-next-landgmickel/flow-next | Skill | 722 | yesterday | MIT | A | 35 | Claude Code, Codex |
| flow-next-worktree-kitgmickel/flow-next | Skill | 722 | yesterday | MIT | A | 43 | Claude Code, Codex |
| development-workflowathola/claude-night-market | Skill | 350 | yesterday | MIT | A | 20 | Claude Code |
| share-a-libraryMoizIbnYousaf/Ai-Agent-Skills | Skill | 1.2k | 1mo ago | MIT | A | 41 | Claude Code, Codex |
| stepwise-task-executionmakifbaysal/tasktrooper | Skill | 122 | today | Apache-2.0 | A | 33 | Claude Code, Codex |
| github-clizhinjs/zhin | Skill | 137 | yesterday | MIT | A | 30 | Claude Code, Codex |