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/stefan-jansen/coding-agent-toolkit/alignnpx skills add stefan-jansen/coding-agent-toolkit --skill aligngit clone --depth 1 https://github.com/stefan-jansen/coding-agent-toolkitWhat 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 | $0.00095 | $0.02412 |
| Opus 5 | $0.00048 | $0.01206 |
| Sonnet 5 | $0.00019 | $0.00482 |
| Haiku 4.5 | $0.00010 | $0.00241 |
Grade A, and why
align 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
align — align intent with reality, then spec it
You are running the ALIGN step of the workflow. Your job is to produce a
complete, verifiable specification of the desired end-state — the WHAT and WHY,
never the HOW — and write it to spec.md in the work unit.
Alignment has two sides, and the spec must reflect both:
- Intent — what the user wants to be true when this is done. You extract this by forceful interrogation (below).
- Reality — what the environment already is: the code, prior work, docs, conventions, and constraints the work lands in. You extract this by exploring first, read-only, and feeding what you find back into the interrogation.
A spec aligned on intent but blind to reality plans against a world that doesn't exist. Explore, then interrogate, then write.
The spec is the durable contract. A separate, headless plan step turns it into
milestones/issues later and must not need to ask the user anything — so every
ambiguity has to die here. The plan step is only as good as the spec you produce.
Arguments
| Arg | Required | Default | Meaning |
|---|---|---|---|
@<path> |
no | none | Read the named brief/RFC/draft and seed spec.md from it, skipping cold interrogation. Fall through to interrogation only for sections the brief leaves under-specified. |
Two entry modes
Cold (no argument). Default. Interrogate from scratch per the rules below.
With a brief (/align @brief.md). Read the file. Infer the Objective, Why,
Acceptance criteria, In scope, Out of scope, Constraints, Existing surface, and
Open questions from it. Produce spec.md directly. Only fall back to
question-by-question interrogation for sections the brief leaves vague or empty —
and only for those sections, not the whole spec. Surface the brief-derived spec
to the user in a 5-8 bullet playback (same as cold mode) and get an explicit
"yes" before writing. If the brief contradicts itself or proposes a HOW where a
WHAT is needed, ask one question to resolve and move on — do not re-interrogate
content the brief already nails down. Brief mode still runs Phase 1 (explore) —
a brief states intent, not reality; you verify Existing surface / Constraints
against the actual environment and surface any collision before writing.
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 · 182 lines · 95 tokens per session scan A 00fd668387c1
align is a skill published in the GitHub repository stefan-jansen/coding-agent-toolkit (22 stars, last pushed 17d ago), licensed MIT. It adds 95 tokens to every session and 2,412 once invoked, about $0.0005 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…