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-whygit 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-why)<a href="https://agentmods.dev/skills/rse/ase/ase-meta-why"><img src="https://agentmods.dev/badge/skills/rse/ase/ase-meta-why.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 | $0.00014 | $0.01878 |
| Opus 5 | $0.00007 | $0.00939 |
| Sonnet 5 | $0.00003 | $0.00376 |
| Haiku 4.5 | $0.00001 | $0.00188 |
Grade A, and why
ase-meta-why scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@${CLAUDE_SKILL_DIR}/../../meta/ase-control.md @${CLAUDE_SKILL_DIR}/../../meta/ase-skill.md @${CLAUDE_SKILL_DIR}/../../meta/ase-getopt.md
$ARGUMENTS
Why ?
For this, iteratively ask "why" to drill down from symptoms to the root-cause. This helps to identify the fundamental reason behind a problem rather than just addressing surface-level symptoms.
-
State the problem statement.
-
Find the root-cause of by following this iteration cycle. Start with a set equal to the .
Determine the maximum chain length from : set to ; if is non-numeric or less than or equal to 0, use the default 5 instead.
Determine the maximum chain width from : set to ; if is non-numeric or less than or equal to 0, use the default 1 instead.
-
Walk a single causality chain (the classic Five-Whys):
Start with 1 (set iteration counter to one).
Ask <question/> and document the answer in <answer/> with the following template. Don't stop at symptoms; keep digging for systemic issues. Consider technical, domain-specific, process-related, or organizational causes. <template> <ase-tpl-bullet-secondary/> **WHY <n/>**: <answer/> </template> Then, for the next iteration, set <question/> now to be the last <answer/>. The magic is NOT in exactly <depth/> "Whys" -- you can <break/> the iteration when you have already reached the root-cause. Finally, set <n/> to <n/> + 1 (increment iteration counter). -
Walk a widened causality chain: at each "why" level, surface up to candidate sub-causes, then commit to the single most significant one and descend into it (the chain stays single-rooted -- the extra candidates are not each drilled to their own root-cause). Their purpose is to guard against premature commitment to the wrong sub-cause: by enumerating the plausible alternatives at each level, the chosen descent is a justified selection rather than the first plausible answer, and the unchosen candidates remain on record as fallbacks to backtrack into (see STEP 3) should the chosen path fail validation.
Remember the unchosen candidates of every level (keep them in , tagged by their level ), so STEP 3 can backtrack into them.
Start with 1 (set iteration counter to one).
Ask <question/> and surface up to <width/> *distinct*, *non-overlapping* candidate sub-causes, each documented in <answer-k/>. Let <count/> be the number of candidates you actually surfaced (at least one, at most <width/>). Don't stop at symptoms; keep digging for systemic issues. Explore *different* candidates -- technical, domain-specific, process-related, or organizational causes -- and avoid restating the same cause in different words.
-
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.
- 8d ago First seen · 191 lines · 14 tokens per session scan A 5d25d5dc5321
ase-meta-why is a skill published in the GitHub repository rse/ase (47 stars, last pushed today), licensed Apache-2.0. It adds 14 tokens to every session and 1,878 once invoked, about $0.0001 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
harness-doctor
Check whether this project's Agentsmith harness is installed correctly and healthy — fires on "is my harness set up right?", "harness doctor", "check my harness". Part of the Agentsmith harness; checks each selected agent's managed rules, settings, skills, hooks, verification, and leanness with a one-line fix for each…
gha
Analyze GitHub Actions failures and identify root causes.
mobile-performance-react-native
React Native performance profiling, optimization, and monitoring - JS/UI thread analysis, re-render prevention, list optimization, image performance, bundle size, startup time, memory leaks, React Compiler, New Architecture benefits.
web-error-handling-error-boundaries
Error boundary patterns, fallback UI, reset/retry, react-error-boundary library, React 19 createRoot error hooks.
api-observability-axiom-pino-sentry
Pino logging, Sentry error tracking, Axiom - structured logging with correlation IDs, error boundaries, performance monitoring, alerting.
api-observability-setup-axiom-pino-sentry
Pino, Axiom, Sentry installation - one-time project setup for logging and error tracking with source maps upload.