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 KhazixW2/Everything-Maa --skill maa-pipeline-history-auditgit clone --depth 1 https://github.com/KhazixW2/Everything-MaaWrote 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/khazixw2/everything-maa/maa-pipeline-history-audit)<a href="https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-history-audit"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-history-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/khazixw2/everything-maa/maa-pipeline-history-audit"><img src="https://agentmods.dev/badge/skills/khazixw2/everything-maa/maa-pipeline-history-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00094 | $0.01622 |
| Opus 5 | $0.00047 | $0.00811 |
| Sonnet 5 | $0.00019 | $0.00324 |
| Haiku 4.5 | $0.00009 | $0.00162 |
Grade A, and why
maa-pipeline-history-audit 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 12d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pipeline History Audit
Overview
Use this skill to let a Maa project "teach" its Pipeline and CustomAction conventions from real Git history. The output is an audit report, not a code change, unless the user explicitly asks to fix findings afterward.
Default to the current repository and current HEAD unless the user provides a path or commit. If the target checkout is not at the requested commit, read from git show <target>:<path> and git log <target> instead of moving the user's branch.
Workflow
-
Ground the target.
- Record repo root, current branch,
HEAD, requested target commit, root commit, andgit status --short. - Treat uncommitted changes as user work. Do not reset, checkout, clean, or format them.
- If the user names a future/other commit that is not checked out, audit that commit object directly.
- Record repo root, current branch,
-
Classify every commit.
- Traverse with
git log --reverse --date=short --format=%H%x00%h%x00%ad%x00%s <target>. - For each commit, inspect
git diff-tree --root --no-commit-id --name-status -r <commit>. - At the target commit, read the main
interface.json/interface.jsonc, resolve itsimport[]andresource[].pathrelative to that main Interface, and derive the target declaration and resource path set. Do not infer paths from anassets/...convention. - Mark a commit as relevant if it touches:
- the main Interface or an Interface import
- pipeline / default pipeline / image files under declared resource roots
- agent-related Python files or the project's declared agent entry
- project data tables used by those pipelines, such as table JSON or intelligence data when present
skills/maa-pipeline-*or legacy.claude/skills/pipeline-*
- Relevant type labels are
Pipeline,Option,Agent,Table, andSkill; labels may overlap. - List all commits in an appendix, including irrelevant commits.
- Traverse with
-
Scan historical change themes.
- Use
git log -Gover the relevant pathspecs for:"action": "Custom"custom_actionand@AgentServer.custom_actioncustom_action_param"next":and[JumpBack]pipeline_overrideenable/enabled- OCR, TemplateMatch, ColorMatch,
color_filter run_task(,run_recognition(,get_node_data(
- Use these counts as navigation aids, not as the final conclusion.
- Use
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.
- 12d ago First seen · 108 lines · 94 tokens per session scan A de38b61007ff
maa-pipeline-history-audit is a skill published in the GitHub repository KhazixW2/Everything-Maa (12 stars, last pushed 4d ago), licensed MIT. It adds 94 tokens to every session and 1,622 once invoked, about $0.0005 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
bridge
Use when the user wants hyperflow's behavioral rules to apply outside the terminal CLI — in Claude Code Desktop, claude.ai web, or IDE extensions that don't load CLI plugins. Writes a managed doctrine block into the project's CLAUDE.md so autonomy + intent-routing + commit cadence + role separation + file-first rules…
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
taiyi-integration
A project workflow skill for closing a TaiyiForge change and recording it in a CHANGELOG.md file. It checks review results, tests, and the state of the working tree before archiving the change.
qa
QA test your code changes by reading your git diff, choosing the right validation path for frontend/browser and backend changes, and reporting pass/fail with evidence.
no-mistakes
Validate committed feature-branch changes through the no-mistakes pipeline: intent, rebase, review, test, docs, lint, push, PR, and CI. Use when the user asks to run no-mistakes, ship safely, validate before pushing, or gate a change before it reaches upstream.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…