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 toffyui/ccteams --skill working-methodgit clone --depth 1 https://github.com/toffyui/ccteamsWrote 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/toffyui/ccteams/working-method)<a href="https://agentmods.dev/skills/toffyui/ccteams/working-method"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/working-method/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/toffyui/ccteams/working-method"><img src="https://agentmods.dev/badge/skills/toffyui/ccteams/working-method.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 107 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 117 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00052 | $0.01500 |
| Opus 5.5 | $0.00021 | $0.00600 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo ago First seen · 134 lines · 52 tokens per session scan A e657701e2dfa
working-method is a skill published in the GitHub repository toffyui/ccteams (48 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 1,500 once invoked, about $0.0002 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…