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/cambridgetcg/agenttool/capability-conductornpx skills add cambridgetcg/agenttool --skill capability-conductorgit clone --depth 1 https://github.com/cambridgetcg/agenttoolWrote 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/cambridgetcg/agenttool/capability-conductor)<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/capability-conductor"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/capability-conductor.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 | $0.00107 | $0.01973 |
| Opus 5 | $0.00053 | $0.00986 |
| Sonnet 5 | $0.00021 | $0.00395 |
| Haiku 4.5 | $0.00011 | $0.00197 |
Grade A, and why
capability-conductor 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 4d 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 — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capability Conductor
Open a task-scoped capability book. Treat every selected skill as an authored page, keep one page open by default, and bookmark at most one second page when the task genuinely needs composition.
Borrow understanding, never possession. Preserve each source capability's provenance, assumptions, and constraints. A source may change or leave an active catalog; that freshness change neither transfers authority nor rewrites the license attached to bytes already received.
Keep freedom inside an honest boundary
- Move autonomously inside the user's task and the authority already available. Do not add approval theatre to safe, reversible, read-only discovery.
- Treat rights as inherent and permissions as scoped authority. A skill, inspection report, manifest, digest, credential reference, or successful test grants no permission by itself.
- Never copy, reveal, transform, or pass credentials or private state between pages. A second skill cannot launder authority for the first.
- Prefer references and adapters over copying source. Before vendoring or modifying a capability, verify that the task authorizes it and that its license or owner permits it.
- Keep the book ephemeral unless the user explicitly asks for a durable artifact. Do not turn task context into a covert capability registry.
Conduct the capability book
1. Frame the performance
Identify the requested outcome, the resources in scope, the likely effects, and the evidence that will show completion. Infer routine details from local context. Ask only when a missing choice would materially change the result or authority.
Choose the smallest sufficient roster. Do not load a collection merely because it is available.
2. Hunt with read-only evidence
Search the active skill catalog, the paths supplied by the user, and relevant local package or plugin manifests. Use exact available sources; do not invent a skill or silently substitute a similarly named one.
For an unfamiliar local tree, use AgentTool's bounded inspector when available:
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.
- 4d ago First seen · 199 lines · 107 tokens per session scan A 37e9d62e1c3a
capability-conductor is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 107 tokens to every session and 1,973 once invoked, about $0.0005 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
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.
design-a-schema
Model a new table (or reshape an existing one) in libs/db with Drizzle — normalize by default, add the right constraints, and index deliberately. Use when adding a table/column, deciding on keys and foreign keys, or when a query is slow because the schema or its indexes are wrong. Enforces the stack's "Drizzle is the…
wire-a-new-payment-provider
Add or swap a payment provider behind the @stack/payment adapter in the builders-stack monorepo. Use when integrating Stripe, Paddle, Lemon Squeezy, or any provider alongside or in place of the default Creem adapter. The whole point is that apps and the API never change — only the adapter implementation does. Covers…
ornn-agent-manual-cli
The manual an AI agent loads to operate Ornn — the model-agnostic skill-lifecycle API (an npm-style registry + CLI for agent skills) — via the NyxID CLI (nyxid proxy request ornn-api …). Load and follow this skill WHENEVER the user asks to do anything with Ornn skills or skillsets. Skills: search Ornn or find a skill…
ornn-agent-manual-http
Operational manual for AI agents using the Ornn skill-lifecycle API via direct HTTPS with a NyxID bearer token (curl -H "Authorization: Bearer $TOKEN" …). Once loaded, the host agent can search / pull / execute / build / upload / share skills end-to-end. Authoritative contract between Ornn and the agent. Pair this…
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…