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/owndiff/own-your-diff/owndiff-pre-commitnpx skills add owndiff/own-your-diff --skill owndiff-pre-commitgit clone --depth 1 https://github.com/owndiff/own-your-diffWhat 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 | $0.00077 | $0.01036 |
| Opus 5 | $0.00039 | $0.00518 |
| Sonnet 5 | $0.00015 | $0.00207 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
owndiff-pre-commit 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.
How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OwnDiff Pre-Commit
Use this skill to produce a verified commit candidate. Stop before committing or pushing unless the user explicitly authorizes that Git action.
Workflow
- Read the latest user request and
git status --short. Treat existing worktree changes as user work; never discard them. - Inspect the complete staged and unstaged diff. Separate release changes from ignored proof, generated artifacts, caches, research, and unrelated edits.
- Run the deterministic audit from the repository root with the repository interpreter:
.venv/bin/python skills/owndiff-pre-commit/scripts/audit.py --repo . --staged --run-checks
If nothing is staged yet, omit --staged for the first diagnostic pass. Stage only confirmed release files, then rerun with --staged.
- Run a leak audit before any commit, push, tag, release, or marketplace/package update:
.venv/bin/python skills/owndiff-pre-commit/scripts/audit.py --repo . --history
The leak audit must cover the current tracked tree, staged diff, unstaged diff, untracked release candidates, and Git history reachable from all local refs. High-confidence private paths or credential patterns are blockers. Redaction markers and secret-adjacent examples are warnings; inspect their context without printing matched text, then remove accidental leaks or document why the warning is an intentional test, security rule, or sanitization example.
- For release work, verify binary integrity before continuing:
- Run
python scripts/verify_release_assets.py --release-dir distafter local release assets are built. - After publishing a tag, run
python scripts/verify_release_assets.py --repo owndiff/own-your-diff --tag <tag>. - Treat a missing binary, missing
.sha256sidecar, invalid checksum file, or checksum mismatch as a release blocker. - The deterministic audit also checks that CI/release workflows keep this verification wired in.
- Run
- Verify documentation semantically:
- Map behavior claims to current code, config, tests, or observed command output.
- Verify unstable install syntax with the installed CLI's
--helpfirst. - When local help is unavailable, use only the agent vendor's official documentation and cite it in the work log.
- Do not claim an agent, command, browser review, or workflow was tested unless it actually ran.
- Remove a document or asset only when it is duplicated, stale, unreferenced, generated, or outside the product's supported workflow. Preserve
README.md,skills/owndiff/SKILL.md,SECURITY.md,CONTRIBUTING.md, licenses, manifests, and referenced media unless evidence shows they are obsolete.
- Run OwnDiff on the exact candidate diff. For medium/high/critical risk, use the active agent model to generate every question and answer choice, validate the response, and complete the real browser review gate.
- Re-run the audit, tests, skill/plugin validators, release-asset verification when applicable, and leak audit after every correction.
- Report:
- changed and removed files;
- documentation claims verified and their evidence;
- test and validator results;
- OwnDiff gate status and attempt summary;
- any residual risk or unavailable agent runtime.
What ships with it
3 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.
- 2d ago First seen · 66 lines · 77 tokens per session scan A 318841e83709
owndiff-pre-commit is a skill published in the GitHub repository owndiff/own-your-diff (4 stars, last pushed 1mo ago), licensed MIT. It adds 77 tokens to every session and 1,036 once invoked, about $0.0004 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
opensrc
Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…
release-cli
Release a new version of the tokenmaxxing CLI to npm. Use when explicitly asked to release or publish @851-labs/tokenmaxxing, including checking main, bumping apps/cli/package.json, updating CHANGELOG.md, committing, tagging cli-vX.Y.Z, pushing, monitoring generated native package publishing, and smoke testing the…
ship-mobile-app
Build, change, debug, and prepare production mobile apps across domain meaning, local and server state, lifecycle, platform, and release boundaries. Use for non-trivial Flutter, React Native, iOS, or Android work involving persistence, sync, auth, offline behavior, notifications, permissions, native integrations…
verify-regression-tests
Verify that a regression test actually detects the defect it claims to guard against. Use after adding or reviewing a bug-fix guard, reproducing the original failure after a fix, or investigating a suspiciously green regression test. Do not use for general TDD, broad test-suite audits, mutation-score optimization…
repository-bootstrap
Audit and establish or upgrade the canonical repository governance baseline. Use only when explicitly asked to bootstrap, standardize, or upgrade a repository; do not use for feature development or source-code restructuring.
repository-hygiene
Perform a read-only evidence-based audit of stale docs, agent files, scripts, generated artifacts, duplicate code, and optional tools. Use only when explicitly asked for cleanup or governance review; do not delete or refactor during the audit.