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-evaluatenpx skills add rse/ase --skill ase-meta-evaluategit clone --depth 1 https://github.com/rse/aseWrote 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/rse/ase/ase-meta-evaluate)<a href="https://agentmods.dev/skills/rse/ase/ase-meta-evaluate"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-evaluate.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00050 | $0.03265 |
| Opus 5 | $0.00025 | $0.01632 |
| Sonnet 5 | $0.00010 | $0.00653 |
| Haiku 4.5 | $0.00005 | $0.00327 |
Grade A, and why
ase-meta-evaluate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
- Output the determined reason with just the following <template/>
and do not output anything else:
<template>
<ase-tpl-bullet-secondary/> **REASON**: *<reason/>*
</template>
</step>
2. - From the derive the two or more alternatives (K=1-N) the user wants to be evaluated. Do not output anything.
- If fewer than two alternatives could be derived (N<2), output the
following <template/> and *stop the entire flow* immediately without
executing any further steps:
<template>
<ase-tpl-bullet-signal/> **ERROR: INSUFFICIENT ALTERNATIVES**: at least two are required for a comparison!
</template>
- For each alternative <alternative-K/> (K=1-N), decide whether
you have all necessary information at hand to give it the proper,
unique, short, and *concise name* <alternative-K/>. If you are
unsure, use the `ase-meta-search` skill (at most one invocation per
alternative, drawing from the *skill-wide shared budget* of at
most 8 `ase-meta-search` invocations in total across STEP 2 and STEP 3
combined) to find out more and adjust the name <alternative-K/>.
If still unsure after the shared budget is exhausted, pick the
best-guess concise name and proceed. Do not output anything.
- For each alternative <alternative-K/> (K=1-N), decide which *one*
of *USP* (Unique Selling Point -- what makes it unique), *Crux*
(what you should notice), or *Gotcha* (what you should not stumble
over) is its single most distinguishing perspective, and remember
this as an <info-K/> (K=1-N) formatted like `<type/>: <hint/>` where
<type/> is one of `USP`, `Crux`, or `Gotcha` and <hint/> is a 1-6
word hint. Do not output anything.
- For the set of alternatives, decide what the 1-6 word long
name of the *class of alternatives* <class-of-alternatives/> is.
Do not output anything.
- For each alternative <alternative-K/> (K=1-N), decide whether
it is a genuine member of <class-of-alternatives/>. If any
<alternative-K/> is *not* a member (i.e. the alternatives are not
mutually comparable within a single class), output the following
<template/> (repeating the `⚑` line once per non-member
alternative, i.e. once for each <alternative-K/> for which the
membership decision was negative) and *stop the entire flow*
immediately without executing any further steps:
<template>
<ase-tpl-bullet-signal/> **ERROR: INCOMPARABLE ALTERNATIVES**: *<class-of-alternatives/>*
⚑ **<alternative-K/>** (*member of a different class*)
</template>
- Output the determined, individual alternatives as a Markdown
*table* with just the following <template/> and do not output
anything else:
<template>
<ase-tpl-bullet-normal/> **ALTERNATIVES**: *<class-of-alternatives/>*
| ⚑ *Alternative* | ⚖ *Hint* |
| :--------------------- | :-------- |
| ⚑ **<alternative-1/>** | <info-1/> |
[...alternatives K=2-(N-1) for N>2...]
| ⚑ **<alternative-N/>** | <info-N/> |
</template>
</step>
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.
- 6d ago First seen · 266 lines · 50 tokens per session scan A e65644954a2d
ase-meta-evaluate is a skill published in the GitHub repository rse/ase (47 stars, last pushed 8d ago), licensed Apache-2.0. It adds 50 tokens to every session and 3,265 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
hns-lsel-curator
Local Self-Evolution Loop (LSEL) curator — the CLUSTER + drain engine for the GOOS-local PROPOSE→APPLY seam closure (SPEC-LSEL-LOCAL-EVOLUTION-001). Companion-offset drain of .moai/lessons-inbox.jsonl with a drain-side severity filter that drops the 65% Bash-timeout/sandbox noise, eventkey clustering with a frequency…
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.
hns-workflow-ci-loop
Unified CI watch + auto-fix loop skill. Polls gh pr checks after /moai sync PR creation, classifies required vs auxiliary failures, attempts safe automated patches (max 3 iterations), and escalates semantic failures to the user. Use for CI loop workflow — NOT for general loop iteration patterns (see…
moai-harness-learner
Harness learning subsystem coordinator. Produces Tier 4 auto-update proposal payloads consumed by the orchestrator (which surfaces them via AskUserQuestion) and orchestrates Apply/Rollback flows. Triggers when harness learning proposals are pending or learning lifecycle management is needed.
moai-kanban-foreman
One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test…
hns-oss-docs-readme-sync
README 4-file synchronization procedure for the oss-docs harness: Korean README.ko.md as primary source, en/ja/zh derivation, the shared language-switcher header contract, section-order parity checklist, and the manual verification recipe (no linter exists for READMEs). Loaded by the content-author and…