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/bendrucker/claude/copilotnpx skills add bendrucker/claude --skill copilotgit clone --depth 1 https://github.com/bendrucker/claudeWhat 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 | $0.00065 | $0.02741 |
| Opus 5 | $0.00032 | $0.01371 |
| Sonnet 5 | $0.00013 | $0.00548 |
| Haiku 4.5 | $0.00006 | $0.00274 |
Grade A, and why
github:copilot scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Agentic mode passes `--allow-all-tools` and subtracts from it: `--deny-tool write` and `--deny-tool url`, plus `shell(git push)`, `shell(gh:*)`, `shell(curl:*)`, and `shell(wget:*)`. Deny beats allow, so those six are th How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Review
A second model reads the diff. The point is a different reviewer rather than a better one: Claude re-reading its own work shares the blind spot that produced it. It has already caught an unchecked-failure defect that two Claude review passes both cleared.
What It Costs
The plan grants 1500 AI credits a month. It resets on the 1st and does not roll over. Four measured facts shape every choice:
- A terra call pays about 3.5 credits before it reads a line of your code, writing 14k tokens of system prompt and tool definitions to cache at 250 credits per million. That is half a median review. A second call is never a rounding error.
- Output costs 6x input and 60x cache_read. Verbose answers run up a bill faster than large diffs.
- Nothing caches between calls. Separate spawns are separate sessions, and each one re-pays its whole prompt at the cache_write rate. Three angles cost three full prompts.
gpt-5.6-lunaprices every token class at exactly a tenth of terra.
Sizing a Review
--status prints the current tier and the bands, and spends nothing. Run it when you are unsure whether a change qualifies.
The tier comes from pace, credits remaining divided by days to reset. Under 25 is constrained, over 60 is abundant, and everything between is normal. The nominal allowance of 48 a day (1500 over 31) is the yardstick --status prints pace against, and it decides nothing on its own. The tier sets how strict the bar is, never how much to spend. Manufacturing reviews to use up an allotment is the failure mode this guards against, so credits left unspent in a month where every qualifying change got a full review are the right outcome.
| tier | gate |
|---|---|
| constrained | terra only on risk-surface hits, luna one-shot otherwise |
| normal | terra one-shot on gate-worthy changes, skip the rest |
| abundant | terra one-shot on any substantial human change, 3 angles on the risk class, agentic available |
The bands reuse ship's Bot Review Gate criteria, so one set of rules decides both:
What ships with it
2 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 · 155 lines · 65 tokens per session scan A 8b06684170bb
github:copilot is a skill published in the GitHub repository bendrucker/claude (16 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 2,741 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…