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 skills add allemaar/open-skills --skill diff-recapgit clone --depth 1 https://github.com/allemaar/open-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/allemaar/open-skills/diff-recap)<a href="https://agentmods.dev/skills/allemaar/open-skills/diff-recap"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/diff-recap.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00144 | $0.03120 |
| Opus 5 | $0.00072 | $0.01560 |
| Sonnet 5 | $0.00029 | $0.00624 |
| Haiku 4.5 | $0.00014 | $0.00312 |
Grade A, and why
diff-recap 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 8d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/diff-recap
Turns a git diff into a recap you can paste into a pull request — a per-file change table whose numbers are transcribed from git, grouped and labelled, rendered as an inline annotated widget with a mandatory ASCII twin, and backed by a diff-recap/1 record. It fills the gap the orient- family leaves open: orient-map shows the shape of the work and orient-status shows where you stand, but neither recaps what a concrete change-set contains for a reviewer. diff-recap does exactly that, and only that.
Its differentiator is true by construction: the structured numbers (per-file added/removed/status and the headline totals) come straight from git diff --numstat and --name-status — the model authors only the prose labels. A record whose totals don't equal the sum of its rows is rejected by a value gate before it can be shown, so the recap cannot quietly lie about the diff. And unlike a hosted recap renderer, it has zero external dependency — the ASCII twin is self-contained and PR-pasteable in any channel.
Structured execution spec:
protocol.yon. Read it for the canonical steps, rules, and gates; this file is the human-readable, self-sufficient explanation. The two must stay in sync — if you edit one, update the other and refresh the@STAMPdate.
When to use
- "Recap this diff / summarize these changes for a PR" — you want a reviewer-ready change summary, not a fresh read of the whole tree.
- "What changed in this branch" as a change-set, grouped by area with a one-line why per file.
- Right before opening a pull request, when you want a paste-able summary whose numbers you can trust.
How it works (self-sufficient — works without protocol.yon)
Every call recomputes from the real diff; nothing is stored.
- Take
range,repo, andintentas inputs — never prompt.rangedefaults to the working tree againstHEAD(or aA..Brange, or--staged);repodefaults to the cwd.intent(the PR's goal) shapes the labels — if it's ungrounded, the recap still emits the mechanical facts but caps the labels to descriptive and never invents a rationale.
What ships with it
11 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.
- examples/bad/fabricated-counts.yon 1.7 KB
- examples/bad/fail-open.yon 1.7 KB
- examples/bad/numstat-mismatch.yon 1.8 KB
- examples/diff-recap.ascii.txt 1.1 KB
- examples/diff-recap.example.yon 2.2 KB
- examples/diff-recap.numstat 85 B
- examples/diff-recap.widget.svg 2.6 KB
- protocol.yon 8.3 KB
- recap-schema.yon 2.3 KB
- references/render-face-contract.md 842 B
- references/tools/diff-recap-check.mjs 18 KB runs code
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.
- 8d ago First seen · 134 lines · 144 tokens per session scan A 5e29e40d28b4
diff-recap is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed 21d ago), licensed Apache-2.0. It adds 144 tokens to every session and 3,120 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
install-skill
Install a community skill pack into this fork from a GitHub repo and ship it as an auto-merged PR.
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
close-task-commit-push-pr
Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.