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/rse/ase/ase-meta-diffnpx skills add rse/ase --skill ase-meta-diffgit clone --depth 1 https://github.com/rse/aseWhat 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 | $0.00057 | $0.04052 |
| Opus 5 | $0.00028 | $0.02026 |
| Sonnet 5 | $0.00011 | $0.00810 |
| Haiku 4.5 | $0.00006 | $0.00405 |
Grade A, and why
ase-meta-diff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
$ARGUMENTS
Procedure
-
-
Determine the diff details by running the corresponding command (taken exactly as given) and capturing the full diff output into for the subsequent analysis:
git diff --cached -
Determine the diff statistics by running the corresponding command (taken exactly as given) and capturing the full stat output into for the subsequent analysis:
git diff --cached --numstat
-
-
-
Analyze the and and synthesize a concise narrative of WHAT changed and WHY, grouped by intent rather than by file. Honor the following intents:
FEATURE: new functionality or configurationIMPROVEMENT: improved functionality or configurationBUGFIX: corrected functionality or configurationUPDATE: updated functionality or configurationCLEANUP: cleaned up functionality or configurationREFACTOR: refactored functionality or configuration
-
<template> <ase-tpl-bullet-normal/> **CHANGE INTENT REPORT**: </template>2. Render a three-column table with one row per discovered intent group present in the . Output the following table header :
<template> | Intent | Changes (LoC) | Files & Description | | ------ | ------------- | ----------------------- | </template>3. For each discovered intent group, emit the following row , where is the intent label, is the total number of lines changed per intent group in format
+N/-M, is the list of affected file references, and is a brief one-to-two-sentence narrative of what changed and why:<template> | **<intent/>** | <changes/> | <files/>: <description/> | </template> In the <files/> part of the second column, mark up all file references as code (with backticks), prepend them with `▢ `, append ` [+N/-M]` (based on the information in <stat/>) to them, and separate them with `, ` (a comma and space). Do *not* repeat file references in the <description/>. Keep the overall report *concise* and *brief*. Try to keep the number of intent groups (table rows) in the range of 1-10. Do *not* output any further explanation. -
The project source artifacts are classified as a black box, so the user does not want the staged changes scrutinized or their coherence, risk, and blast-radius findings surfaced. The requested scrutiny of STEP 3 through STEP 5 is therefore suppressed: only output the following and then SKIP the remaining steps STEP 3 through STEP 5:
-
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.
- 2d ago First seen · 381 lines · 57 tokens per session scan A 93ca42b6e367
ase-meta-diff is a skill published in the GitHub repository rse/ase (47 stars, last pushed 5d ago), licensed Apache-2.0. It adds 57 tokens to every session and 4,052 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 2026-08-30.
Other skills, from other repositories
moai-ref-git-workflow
Git workflow patterns, branch strategies, conventional commits, and PR templates reference for git operations. Agent-extending skill that amplifies manager-git expertise with production-grade git workflow patterns. NOT for: code implementation, testing, architecture design, documentation content.
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.
landing
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
commit
Create a focused commit from the current staged changes. Use when asked to commit, prepare a commit, or finalize a Symphony-for-Trello issue branch.
eng-conventional-commit-helper
Create conventional commits with clear scope and intent.
ship
Build, commit, push & version bump workflow - automates the complete release cycle.