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/terry-mao/aicodingflow/write-product-specnpx skills add Terry-Mao/AICodingFlow --skill write-product-specgit clone --depth 1 https://github.com/Terry-Mao/AICodingFlowWhat 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 | $0.00020 | $0.00690 |
| Opus 5 | $0.00010 | $0.00345 |
| Sonnet 5 | $0.00004 | $0.00138 |
| Haiku 4.5 | $0.00002 | $0.00069 |
Grade A, and why
write-product-spec 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-product-spec
Write the product contract an implementer and reviewer can use to agree on observable behavior. This is a local shared skill; wrappers may provide exact inputs and output paths that take precedence.
Decide and prepare
Use it when behavior, scope, risk, or user impact is substantial enough that a checked-in spec will reduce ambiguity. Skip it for small fixes, straightforward refactors, and narrow low-risk changes.
Specs normally live under specs/. Without an explicit wrapper or prompt path,
use specs/<topic>/product.md; preserve this repository's lowercase filenames
and issue-backed layout. Do not create an issue or other tracker item unless
the user explicitly asks.
Gather only the feature summary, affected users/consumers, desired behavior, edge cases, validation needs, and relevant issue context. Here, “user” may be an end user, maintainer, operator, API caller, contributor, or agent consuming the designed surface. Ask about missing product decisions instead of guessing.
For UI or interaction work, ask whether a Figma mock exists before drafting
behavior. Include its link, or explicitly write Figma: none provided; skip
this for non-visual features.
Write the spec
Keep the spec implementation-light. Required sections are:
- Summary — the feature and desired outcome in 1–3 sentences.
- Problem — the user or product problem when it is not already obvious.
- Goals — observable outcomes the change must achieve.
- Non-goals — adjacent work that is intentionally out of scope.
- Figma / design references — only for visual work; include the link or explicit absence.
- User experience — the main contract. Prefer numbered, testable behavior invariants covering defaults, inputs, state transitions, loading/empty/error states, cancellation, stale or missing data, permissions, races, and keyboard/accessibility expectations when relevant.
- Success criteria — concrete outcomes a reviewer can observe; do not duplicate the behavior section with generic quality claims.
- Validation — how the behavior will be checked with tests or manual evidence. Keep implementation-specific test design in the tech spec too.
- Open questions — unresolved product decisions, preferably next to the behavior they affect.
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 · 69 lines · 20 tokens per session scan A 1db722c2befc
write-product-spec is a skill published in the GitHub repository Terry-Mao/AICodingFlow (165 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 690 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…