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/voytechg/spec-driven-development/maintain-project-docsnpx skills add VoytechG/spec-driven-development --skill maintain-project-docsgit clone --depth 1 https://github.com/VoytechG/spec-driven-developmentWhat 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 | $0.00029 | $0.00608 |
| Opus 5 | $0.00015 | $0.00304 |
| Sonnet 5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
maintain-project-docs 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintain Project Docs
Update the touched area's active docs in the same batch as the code. Keep active docs small. Historical decisions, verification logs, and archived plans should be created or linked only when they add durable retrieval value.
Workflow
- Identify the touched area(s). Cross-check the files changed against the
Path:entries inAREAS.md. - Open each touched area's
implementation-status.md, if present. Keep it to current state, next checkpoint, known gaps, active plan pointers, and latest verification. Move older verification detail tologs/verification.mdwhen it starts to dominate the file. - Update the active spec only when the contract changed. Use
spec.md,product-spec.md, or the activespecs/<date>-<feature>.md, depending on the area's convention. Keep acceptance checks inside the spec unless the area intentionally maintains a separateacceptance-criteria.md. - Update
acceptance-criteria.mdonly when it exists and is actively used. It is optional; do not create it for small areas when spec-local acceptance checks are enough. - Update
operations.mdonly for operational behavior. Examples: commands, environment variables, paid-call gates, deploy/import/export steps, retry paths, and stop conditions. - Add durable decisions without loading full history.
- Prefer creating a new file under
decisions/YYYY-MM-DD-short-title.mdusing the decision-record template. - Update
decisions/README.mdonly as a short index, if the area has one. - Do not append long chronological entries to an active working doc.
- Prefer creating a new file under
- Update
README.mdwhen the reading order, area focus, active spec pointer, or docs layout changed. - Use the no-doc-change escape hatch only when appropriate. If code changed but the area contract, current state, operations, acceptance checks, and decisions did not change, do not make a noisy docs edit. Instead, include
Docs unchanged by design: <reason>in the final response. - If an expected active doc is missing, propose creating it from
templates/. Do not silently skip. - Confirm in your reply which docs were updated, or give the
Docs unchanged by design:reason. Only then claim the work is done.
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 · 37 lines · 29 tokens per session scan A 22a34a6a7688
maintain-project-docs is a skill published in the GitHub repository VoytechG/spec-driven-development (4 stars, last pushed 3mo ago), licensed MIT. It adds 29 tokens to every session and 608 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 2026-08-31.
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.