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/juanmhidalgo/claude-pluginsWrote 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/commands/juanmhidalgo/claude-plugins/staged-pipeline)<a href="https://agentmods.dev/commands/juanmhidalgo/claude-plugins/staged-pipeline"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/staged-pipeline/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/commands/juanmhidalgo/claude-plugins/staged-pipeline"><img src="https://agentmods.dev/badge/commands/juanmhidalgo/claude-plugins/staged-pipeline.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 | $0.00044 | $0.02211 |
| Opus 5 | $0.00022 | $0.01105 |
| Sonnet 5 | $0.00009 | $0.00442 |
| Haiku 4.5 | $0.00004 | $0.00221 |
Grade A, and why
staged-pipeline 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 today.
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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
- Current branch: !
git branch --show-current - Staged files: !
git diff --cached --name-only - Focus area: $ARGUMENTS
Phase 0: Validate
- Check staged changes exist:
git diff --cached --name-onlymust return files. If empty, STOP and tell user to stage changes first. - Note the staged file list for later phases.
Phase 1: Review (dispatched)
<iron_law priority="blocking">
The reviewer runs in a subagent, and so does the verifier in Phase 2. Neither runs in this conversation.
</iron_law>
This pipeline runs in the session that wrote the staged code. That session holds every reason the code looks correct — which is the framing both the review and the verification must start without.
Use the Agent tool with subagent_type="code-review:branch-reviewer".
Pass scope, not content. Do not summarize the change, explain its intent, or paste excerpts — each transmits the framing the fresh context exists to exclude:
SCOPE: staged changes (git diff --cached)
EFFORT: <low|medium|high|max, default medium>
FOCUS: <the focus area from $ARGUMENTS, if one was given>
OUTPUT_PATH: <scratchpad dir>/staged-pipeline-review.md
The finding format, severity/confidence rubric, labels, and the mandatory
failure-scenario field come from the branch-review skill. Do not restate
the rubric in the agent prompt — the skill is the single source of truth, and a
second copy here is a copy that drifts.
Read OUTPUT_PATH first — it is the primary channel. Use anything returned
inline only to fill in a missing or empty file. If the agent finished and left
neither, the review did not run: say so and re-run it. Never treat a missing
report as a clean one.
Phase 2: Verify (dispatched)
Every finding is verified by an agent that did not produce it. Follow
references/verification.md in the branch-review skill for the dispatch
shape, verdict handling, the empty-refutation rule and the silent-verifier rule.
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.
- today Changed · +22 lines 8991787c1484
- 9d ago First seen · 232 lines · 44 tokens per session scan A 9447df75e3d2
staged-pipeline is a command published in the GitHub repository juanmhidalgo/claude-plugins (8 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 2,211 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
review-diff
Review the current working diff for correctness, security, and reuse.
elegant-code-review
Review the current working diff against the elegant-code decision ladder and propose deletions, honoring the negligence floor.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
prp-commit
Quick commit with natural language file targeting: describe what to commit in plain English.
fix-comments
Address PR review comments by implementing requested changes automatically.
validate-pr-description
Use when validating a PR title and description for conventional commit format, issue linking keywords, and template compliance before submission.