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 tunahanaliozturk/atelier --skill capability-routinggit clone --depth 1 https://github.com/tunahanaliozturk/atelierWrote 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/tunahanaliozturk/atelier/capability-routing)<a href="https://agentmods.dev/skills/tunahanaliozturk/atelier/capability-routing"><img src="https://agentmods.dev/badge/skills/tunahanaliozturk/atelier/capability-routing/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/tunahanaliozturk/atelier/capability-routing"><img src="https://agentmods.dev/badge/skills/tunahanaliozturk/atelier/capability-routing.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.00313 |
| Opus 5 | $0.00014 | $0.00156 |
| Sonnet 5 | $0.00005 | $0.00063 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
capability-routing 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 11d 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.
What it actually says
Capability Routing
Route each task with the lib/routing.mjs helper, then apply judgment:
- Build the task descriptor
{ kind, layer?, capabilities? }from the planner's tagged step. The registry is in context from the SessionStart hook; if it is not (a session started without the hook), read theagents/directory withreadRegistryfirst. - Call
route(task, agents). It coarse-filters bylayerandtask_kinds, scores each candidate bytask_kindsandcapabilitiesoverlap, and breaks ties deterministically (score descending, then name ascending). - If
routereturnsfallback: true, no agent fits. Do not force a poor match: tell the user and use the writing-agents skill to scaffold a new agent that follows the capability schema. - Otherwise take
pickas the default. You may override it for a documented reason by reading the candidates'descriptions — but record the final choice and thereason(including the score) in the mission decision log.
The orchestration and review layers are cross-cutting: the planner, lead, and reviewers
are invoked by name in a fixed order, not selected by this filter.
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.
- 11d ago First seen · 25 lines · 27 tokens per session scan A 102d8325a06b
capability-routing is a skill published in the GitHub repository tunahanaliozturk/atelier (1 stars, last pushed 2mo ago), licensed MIT. It adds 27 tokens to every session and 313 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 2026-08-31.
Other skills, from other repositories
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
evolve
Research-driven multi-cycle improvement director. Forms causal hypotheses about why scores are low, validates them with scout agents before attacking, dispatches axis-parallel fleet attacks, extracts transferable patterns, and runs indefinitely within a budget envelope. Accumulates a persistent belief model and…
research
Focused research investigations. Converts questions into structured findings with confidence levels and source citations. Single agent by default; with --parallel (or when the question decomposes into 3+ independent angles) it spawns scout agents whose findings are compressed into a unified brief. Does not make…
pr-watch
Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
qa
Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).