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/duoduoler-ops/table-github-capability-router/optimize-agent-capabilitiesnpx skills add duoduoler-ops/Table-GitHub-Capability-Router --skill optimize-agent-capabilitiesgit clone --depth 1 https://github.com/duoduoler-ops/Table-GitHub-Capability-RouterWhat 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 | $0.00054 | $0.00357 |
| Opus 5 | $0.00027 | $0.00179 |
| Sonnet 5 | $0.00011 | $0.00071 |
| Haiku 4.5 | $0.00005 | $0.00036 |
Grade A, and why
optimize-agent-capabilities 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 2d 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
Optimize Agent Capabilities
Treat the repository's L0-L4 documents and templates as the source of truth. This Skill is an optional execution entry, not a second routing specification.
Workflow
-
Run the read-only inventory:
node <skill-dir>/scripts/audit.mjs --json -
Read only the matching profile in
profiles/. -
Classify every detected client:
audit-only: report findings and a client-specific plan; do not edit client configuration.unknown: use the generic profile and do not infer configuration keys or paths.
-
Compare findings with the shared L0-L4 model and propose the smallest useful routing plan.
-
Report detected roots, counts, support boundaries, unsupported assumptions, and next steps.
Safety
- This integration is read-only. Do not install, uninstall, enable, disable, or rewrite anything.
- Do not edit extension caches directly.
- Do not claim support from format similarity alone; client discovery and invocation controls differ.
- Preserve explicit invocation wherever the client supports it.
- Unknown clients receive a plan, not guessed mutations.
Extending Clients
Add a profile first. A future PR may propose a write-capable adapter only when all five operations
are deterministic and tested: detect, inventory, plan, apply, and verify. See
references/client-adapters.md.
What ships with it
9 files 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.
- 2d ago First seen · 42 lines · 54 tokens per session scan A e41c37959176
optimize-agent-capabilities is a skill published in the GitHub repository duoduoler-ops/Table-GitHub-Capability-Router (120 stars, last pushed 18d ago), licensed MIT. It adds 54 tokens to every session and 357 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.