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 rse/ase --skill ase-meta-mintgit 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-mint)<a href="https://agentmods.dev/skills/rse/ase/ase-meta-mint"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-mint.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 | $0.00087 | $0.01566 |
| Opus 5 | $0.00044 | $0.00783 |
| Sonnet 5 | $0.00017 | $0.00313 |
| Haiku 4.5 | $0.00009 | $0.00157 |
Grade A, and why
ase-meta-mint scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
$ARGUMENTS
-
-
Set and set to with any leading and trailing whitespace stripped.
-
Determine the number of identifiers to mint: set to ; if is non-numeric, less than 1, or greater than 100, use the default 1 instead.
-
Set and (set both to empty).
-
-
-
Call the
ase_mint(type: "<type/>", hint: "<hint/>", count: <count/>)tool of theaseMCP server and set to the returned lines of itstextoutput, one identifier per line. You MUST NOT derive a UUID or a SHA-1 digest yourself -- only the tool hashes correctly and reproducibly.
-
-
-
Distill into its essential words: drop filler words, articles, and prepositions, keep the two to four words which carry the actual meaning, and order them from the most general to the most specific one. Prefer established terminology of the surrounding domain over invented wording. Do not output anything.
-
Assemble distinct candidates from these words, ordered best-first, honoring the rules of :
-
const: anUPPER_SNAKE_CASEconstant identifier such asFOO_BAR_QUUX-- upper-case ASCII words joined by_, never starting with a digit. -
var: alowerCamelCasevariable identifier such asfooBarQuux-- the last part MUST be a substantive (Quux) naming what the value is, never a verb, as a variable holds a thing and not an action. -
func: alowerCamelCasefunction identifier such asfooBarQuux-- the first part MUST be a verb (foo) naming what the function does, as a function performs an action and does not hold a thing. -
class: anUpperCamelCaseclass identifier such asFooBarQuux-- a substantive phrase naming the modeled entity, in singular form and without aTheprefix. -
path: akebab-casepath component such asfoo-bar-quux-- lower-case ASCII letters, digits, and-only, never starting or ending with-. -
name: anUpperCamelCaseproduct name such asFooBarQuux-- optimize for a brand, not for a description: short (preferably two to three syllables), pronounceable, memorable, and distinctive. Coinages, blends, and evocative metaphors are explicitly welcome here, and a plain concatenation of the hint words is explicitly not.
-
-
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.
- 7d ago First seen · 158 lines · 87 tokens per session scan A 6b5b3682d56b
ase-meta-mint is a skill published in the GitHub repository rse/ase (47 stars, last pushed 9d ago), licensed Apache-2.0. It adds 87 tokens to every session and 1,566 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 2026-08-30.
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-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-moaiadk-patterns
Skill "hns-moaiadk-patterns" from modu-ai/moai-adk, covering moai-adk-go domain patterns, architecture quick reference, key source paths, pipeline specialist delegation map and template-first build cycle.
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.