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.
npx agentmods add skills/photostructure/coding-skills/review-stagednpx skills add photostructure/coding-skills --skill review-stagedgit clone --depth 1 https://github.com/photostructure/coding-skillsWrote 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/photostructure/coding-skills/review-staged)<a href="https://agentmods.dev/skills/photostructure/coding-skills/review-staged"><img src="https://agentmods.dev/badge/skills/photostructure/coding-skills/review-staged.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 | $0.00055 | $0.00709 |
| Opus 5 | $0.00028 | $0.00354 |
| Sonnet 5 | $0.00011 | $0.00142 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
review-staged 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 5d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Git Staged Changes
Review the staged diff (git diff --cached) for potential issues and
improvements, then prepare the commit. When the user supplies a proposed commit
message, use it as context for the intended change, not as a correctness
requirement.
Leaf-mode guard
If the task identifies your role as leaf-reviewer or sets
delegation-budget: 0, read and follow
../review/references/single-pass.md,
complete one review yourself, return the report to the caller, and stop before
the commit flow below.
Run the review
Size the scope before reading it: git diff --cached --stat. Review all staged
content as supplied. The size or coherence of a proposed commit does not affect
the review verdict.
With the staged diff as the scope, read and follow
../review/references/single-pass.md, then
../review/references/orchestration.md.
The latter's user-facing response rules replace the former's leaf return
behavior.
After the findings, use the shared Commit notes section for optional message
or grouping advice. If a split would improve reviewability or make later reverts
safer, identify the files or hunks in each independently committable batch and
give a complete Conventional Commit message for every batch. State the specific
reason for the split; size alone is not enough. These notes never receive a
priority and never change the verdict. If they are the only concerns, return
Verdict: LAND and No issues found.
Post-review commit flow
If the verdict is DISCARD, explain why the change should not land and stop. Do not prepare a commit message for a change the review recommends abandoning.
Otherwise, do not commit during the review:
- List the files (and line ranges, if partial) that are staged for commit.
- Present the recommended commit message, or the batches and messages from the
Commit notessection. When no note was warranted, confirm the supplied message or draft one. Emphasize motivation or consequence rather than restating the diff. Ask the user to review or edit the proposal. - Only commit after explicit user approval.
What ships with it
1 file 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.
- 5d ago First seen · 68 lines · 55 tokens per session scan A c585928e6137
review-staged is a skill published in the GitHub repository photostructure/coding-skills (3 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 709 once invoked, about $0.0003 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 skills, from other repositories
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
phx-pr-review
Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
privacy-guard
Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…
decision-records
Creates, supersedes and validates decision records (ADRs) against the convention a collection already follows, instead of imposing a published one. Use when the user wants to record a decision, write an ADR, supersede an existing decision, audit or lint a decisions folder, check that an ADR index is in sync, or asks…