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-tech-specnpx skills add Terry-Mao/AICodingFlow --skill write-tech-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 | $0.00021 | $0.00650 |
| Opus 5 | $0.00010 | $0.00325 |
| Sonnet 5 | $0.00004 | $0.00130 |
| Haiku 4.5 | $0.00002 | $0.00065 |
Grade A, and why
write-tech-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 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
write-tech-spec
Translate approved product intent into an implementation plan that fits the existing codebase. This is a local shared skill; wrappers may provide exact inputs and output paths that take precedence.
Decide and research
Use it when work spans modules, has architectural tradeoffs, needs a migration or rollout plan, or benefits from review before implementation. Skip it for straightforward fixes, small refactors, and narrow UI changes with no technical ambiguity. Prefer a product spec first; an end-to-end prototype can be a better precedent when the implementation is still uncertain.
Before drafting, read the product spec when present and inspect the actual repository. Identify current behavior, relevant files/types/entry points, data or control flow, ownership boundaries, dependencies, risks, and validation constraints. Do not infer architecture that can be read from code.
When a code reference matters, pin it to the inspected commit SHA and include a
repo-relative path with line numbers. Add a GitHub blob/<sha>/...#Lx-Ly link
when the repository has an accessible remote; otherwise keep the local
reference. Reference the product spec for behavior rather than restating it.
Write the spec
Use the following core sections, keeping each only as detailed as the decision requires:
- Problem — the technical problem and its product relationship.
- Relevant code — files, symbols, entry points, and current ownership.
- Current state — how the system works and limitations that matter.
- Proposed changes — affected modules, types/APIs/state, data flow, ownership boundaries, sequencing, and tradeoffs.
- Testing and validation — map tests, manual checks, screenshots/videos, or other evidence to the product behavior and its numbered invariants.
Add these sections when they add signal:
- End-to-end flow — when tracing the main path clarifies the change list.
- Risks and mitigations — when there are real regression, migration, rollout, or compatibility hazards.
- Follow-ups — when there is deferred technical debt or an open technical question.
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 · 67 lines · 21 tokens per session scan A fd26cfa5123f
write-tech-spec is a skill published in the GitHub repository Terry-Mao/AICodingFlow (165 stars, last pushed 4d ago), licensed MIT. It adds 21 tokens to every session and 650 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…