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/bikeread/promethos/plan-agent-implementationnpx skills add bikeread/promethos --skill plan-agent-implementationgit clone --depth 1 https://github.com/bikeread/promethosWhat 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 | $0.00022 | $0.00621 |
| Opus 5 | $0.00011 | $0.00311 |
| Sonnet 5 | $0.00004 | $0.00124 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
plan-agent-implementation 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 3d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Produce a clear implementation sequence that can be executed incrementally and verified along the way.
Inputs
- Approved architecture
- Relevant codebase context
- Constraints on tooling, time, and verification
Non-Goals
- Revisiting the architecture without evidence
- Writing vague tasks that hide complexity
Workflow
Trigger signals
- Architecture is approved but no build order exists
- User says "接下来怎么搞" or "what do we build first"
- The conversation is about to jump from design to code without a task breakdown
1. Freeze the implementation surface
Translate the architecture into concrete files, modules, or documents to create or modify, and assign each one a single responsibility. Success criteria: The work is decomposed into concrete units instead of one large implementation blob.
2. Define thin, verifiable tasks
Break the work into steps that each produce a visible result and can be checked independently. Success criteria: Each task is small enough to execute and verify without guessing hidden substeps.
3. Order tasks by dependency and risk
Sequence the work so foundations come first, risky assumptions are tested early, and later tasks build on already verified behavior. Success criteria: The task order reflects both dependency flow and risk reduction.
4. Attach verification to every stage
State the command, inspection, or artifact review that proves each stage is actually complete. Success criteria: The plan defines evidence for every meaningful step, not just activity labels.
5. Decide where reusable eval coverage is required
For any behavior change, recovery path, or safety-sensitive flow, state whether the implementation plan must add or refresh reusable regression or evaluation coverage. Success criteria: The plan makes explicit when verification ends at the current change and when it must be promoted into reusable eval coverage.
6. Check the plan against scope discipline
Review the plan for YAGNI violations, unresolved architecture questions, and tasks that are too vague or too broad. Success criteria: The final plan is narrow, executable, and aligned with the approved design.
What ships with it
1 file 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.
- 3d ago First seen · 84 lines · 22 tokens per session scan A 2445a8862147
plan-agent-implementation is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 621 once invoked, about $0.0001 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.
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…