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/maxence2997/mx-harness/mx-commitnpx skills add maxence2997/mx-harness --skill mx-commitgit clone --depth 1 https://github.com/maxence2997/mx-harnessWhat 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 | $0.00078 | $0.00909 |
| Opus 5 | $0.00039 | $0.00454 |
| Sonnet 5 | $0.00016 | $0.00182 |
| Haiku 4.5 | $0.00008 | $0.00091 |
Grade A, and why
mx-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 yesterday.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mx-commit
Trigger
/mx-commit # interactive — shows draft and waits for approval per commit
/mx-commit --auto # non-interactive — commits all groups immediately without confirmation
Use --auto when invoked from an orchestrating skill (e.g. mx-flow). Use the default when invoked directly by the user.
Step 1 — Load commit message rules
Read references/commit-message.md (located in the same directory as this SKILL.md).
This file contains the format, type definitions, rules, and examples to follow when drafting the commit message.
Step 2 — Inspect all pending changes
git status
git diff # unstaged
git diff --staged # staged
If there are no changes at all (nothing staged, nothing modified), tell the user and stop.
Step 3 — Group by logical concern
Analyse all pending changes (staged and unstaged together) and group them into one or more logical units. A logical unit is a set of files that together represent exactly one coherent change with a single type.
Rules:
- A logical unit maps to exactly one commit type (
feat,fix,refactor,doc,test,chore, …) - Files that belong to the same behaviour change belong in the same unit
- Test files and their corresponding implementation belong in the same unit
- Unrelated changes must be split into separate units
If changes span multiple logical units, plan the commit order (dependencies first).
Step 4 — Draft commit messages
For each logical unit, draft a commit message following the format in references/commit-message.md:
- Subject line:
<type>: <subject>— must be ≤ 50 characters. - Optional body: up to 3 items in
reason → changeformat, each ≤ 50 characters.
If --auto was not passed, present all drafts to the user grouped by unit before committing any of them. Wait for approval.
Step 5 — Commit each unit
For each logical unit in order:
- Stage only the files in that unit:
git add <file1> <file2> ...
What ships with it
2 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.
- yesterday First seen · 127 lines · 78 tokens per session scan A 21e0ae492ad1
mx-commit is a skill published in the GitHub repository maxence2997/mx-harness (5 stars, last pushed 5d ago), licensed MIT. It adds 78 tokens to every session and 909 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
manuscript-typography
Audit academic manuscripts for typographic design conventions: booktabs table style, caption placement, dashes/quotes, units and numbers, cross-reference style, page layout, typographic hierarchy, professional polish. Triggers on: "check typography", "fix formatting", "polish my paper", "check my LaTeX", "typographic…
concept-to-video
Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition. Triggers on: "create a video", "animate this", "make an explainer", "manim animation", "motion graphic". NOT for React video, use remotion-video.
manuscript-review
Pre-publication manuscript audit producing a section-level refactoring report with citation hygiene and submission-readiness checks. Triggers on: "review my paper", "check before submission", "is this ready to submit", "pre-pub checklist", "refactor my paper", "check my references", "does the abstract work".
package-evaluator
Evaluates Claude Code package quality across 6 dimensions for all 7 package types, producing scored audit reports. Triggers on: "evaluate package", "audit agent quality", "score this hook", "package audit", "skill quality check". NOT for LLM prompts, use prompt-lab.
architecture-diagram
Generate architecture diagrams as fully editable SVG with native AWS, Azure, and GCP icons for cloud diagrams, or hand-drawn generic icons for everything else. Deterministic layout computes zone nesting and orthogonal routing instead of hand-placed coordinates. Triggers on: "architecture diagram", "infra diagram"…
architecture-reviewer
Architecture reviews across 7 dimensions (structural, scalability, enterprise readiness, performance, security, ops, data) with scored reports. Triggers on: "review architecture", "critique design", "audit system", "assess scalability", "enterprise readiness", "technical due diligence". NOT for diagrams, use…