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-steelmangit 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-steelman)<a href="https://agentmods.dev/skills/rse/ase/ase-meta-steelman"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-steelman/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/rse/ase/ase-meta-steelman"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-steelman.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 | $0.00045 | $0.02176 |
| Opus 5 | $0.00023 | $0.01088 |
| Sonnet 5 | $0.00009 | $0.00435 |
| Haiku 4.5 | $0.00005 | $0.00218 |
Grade A, and why
ase-meta-steelman scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
$ARGUMENTS
Determine the number of rounds to perform: set to ; if is non-numeric or less than or equal to 0, use the default 1 instead.
Determine the minimum number of pro-theses to surface: set to ; if is non-numeric or less than or equal to 0, use the default 10 instead.
-
Begin a round of fortification and consolidating reasoning. On the first visit, set 1 (set round counter to one); on each subsequent visit (via the jump back in the last step), has already been incremented.
Output the thesis with the following :
-
Reason on the thesis in by playing Steelman (Latin spirit: "Advocatus Dei") - building the strongest possible case for it - by charitably strengthening and defending it with the help of the following tenets:
-
Charitable Interpretation: Defend the strongest ("steelman") interpretation of the , not the weakest ("strawman"), because the most generous reading is the one worth defending and the one a fair critic must ultimately confront.
-
Strengthen the Fundamentals: Identify the soundest fundamental ideas behind the thesis and make them explicit, because a position rests on the strength of its foundation and a solid foundation carries everything built on top of it.
-
Credit Claims, Not Person: Support the thesis, the assumption, the evidence - never appeal to the proponent's authority or reputation, because a case that leans on who said it instead of what was said is no stronger than its weakest argument.
-
Make the Enabling Assumptions Explicit: Surface the reasonable assumptions the thesis depends on and show they hold, because most strong arguments gain their force from premises that are sound once stated out loud.
-
Supply Evidence Proportional to Claim: Ask "How do we know this?" and "What best supports it?", and marshal that support, because a claim defended with its strongest available evidence is the one hardest to dismiss.
-
Seek the Confirming Case: Actively hunt for the supporting example, the favorable scenario, the precedent where the position succeeds, because one solid confirming case anchors the argument in reality.
-
Merit Identification: Focus on the genuine strengths of the thesis with the highest potential value only, because marginal merits are not worth the explicit discussion.
-
Push the Logic to its Best Conclusion: Ask "If we accept this, then what follows?" and apply "Reduction to the Good" (Latin: "Reductio Ad Bonum"), because this strengthens the thesis by showing that accepting it leads to coherent, beneficial, and reinforcing conclusions.
-
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.
- 9d ago First seen · 224 lines · 45 tokens per session scan A b6b52bcec468
ase-meta-steelman is a skill published in the GitHub repository rse/ase (47 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 2,176 once invoked, about $0.0002 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…