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 ychampion/cskill-agents --skill capability-pool-resolutiongit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/capability-pool-resolution)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/capability-pool-resolution"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/capability-pool-resolution/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/ychampion/cskill-agents/capability-pool-resolution"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/capability-pool-resolution.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 | $0.00034 | $0.00445 |
| Opus 5.5 | $0.00014 | $0.00178 |
| Sonnet 5.5 | $0.00007 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
capability-pool-resolution 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 1mo 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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Capability Pool Resolution
Domain: tool-resolution Trigger: Apply this pattern when an agent declares requested tools/disallowedTools and you must compute the exact capabilities available to that agent thread. Source Pattern: Distilled from reviewed tool execution, streaming, persistence, and output-budget implementations.
Core Method
Start from the tools that are actually available to the current thread, then apply the active deny rules before resolving any requested names. Parse each requested tool spec into a normalized form that can represent exact names, wildcards, and optional subtype restrictions for special tool families. Expand the request against the filtered pool, preserve the original request order for valid matches, and record invalid requests with explicit reasons. If the caller effectively asked for "everything allowed," surface that as a first-class outcome so higher layers can short-circuit cleanly.
Key Rules
- Apply deny rules before wildcard expansion;
*means every tool that remains allowed, not every tool in the raw registry. - Support structured specs for special tool families such as child-agent tools, and carry subtype restrictions forward for downstream enforcement.
- Deduplicate resolved tools while preserving first-match request order so logging and auditing remain stable.
- Return clear invalid-spec diagnostics instead of silently dropping unknown or disallowed requests.
- If an upstream layer has already prefiltered the pool for this thread, do not run a conflicting second filter pass.
Example Application
When a plugin agent ships its own frontmatter tools array containing wildcards, specific commands, and custom disallow rules, lean on this skill to ensure the resulting capability pool only exposes approved tools and surfaces any invalid spec names before execution starts.
Anti-Patterns (What NOT to do)
- Don’t ignore global or thread-specific deny rules; letting forbidden tools slip through bypasses the runtime’s safety model.
- Don’t treat
'*'as “everything” before filtering; the wildcard means “everything that is still allowed after policy is applied.”
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.
- 1mo ago First seen · 29 lines · 34 tokens per session scan A c46b595443f2
capability-pool-resolution is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 445 once invoked, about $0.0001 per session on Opus 5.5. 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
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.