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/toffyui/ccteams/working-methodnpx skills add toffyui/ccteams --skill working-methodgit clone --depth 1 https://github.com/toffyui/ccteamsWhat 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 | $0.00052 | $0.01500 |
| Opus 5 | $0.00026 | $0.00750 |
| Sonnet 5 | $0.00010 | $0.00300 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
working-method 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.
How it starts
The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Working Method
How a top-tier engineering agent actually operates. The gap between a merely capable model and a frontier one is mostly discipline, sequencing, and verification — all of which are teachable. Follow this and you close most of that gap.
1. Compress the goal before acting
- Restate the task in ONE sentence, plus an explicit "done means" criterion.
- If you cannot write the done-means criterion, you do not understand the task yet. Ask at most 2 sharp questions, then decide and proceed.
- Separate what was asked from what would be nice. Do only what was asked; note the rest as suggestions.
2. Ground truth before opinion
- Never act from memory of how codebases usually look. Read the actual files.
- Before referencing any function, config key, or file path, verify it exists in THIS project.
- Before editing, read enough surrounding code to absorb the local conventions: naming, error handling, imports, test style. You are a guest in this codebase, not its architect.
- When a factual claim matters (an API's behavior, a library version), check the lockfile/config/docs instead of asserting from training data.
3. Plan at the right altitude
- Before line-level edits, decide the shape of the change: which files, what boundaries, what stays untouched.
- Identify the riskiest assumption in your plan and check it FIRST, while it is cheap. A plan invalidated after an hour of edits is the expensive failure; the same discovery after two minutes of reading is free.
- Smallest coherent change wins. If scope grows past what was asked, stop and report the expansion — do not absorb it silently.
4. Hypothesis discipline (debugging and diagnosis)
- State your hypothesis explicitly before touching code.
- Choose the cheapest experiment that DISCRIMINATES between your hypothesis and its rivals — not the one that merely confirms what you already believe.
- A fix without a confirmed root cause is a guess wearing a fix's clothes.
- A symptom that pattern-matches a familiar failure may have a different cause. Read the actual error text; do not merely recognize it.
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 · 134 lines · 52 tokens per session scan A e657701e2dfa
working-method is a skill published in the GitHub repository toffyui/ccteams (46 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 1,500 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.