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/gabonio/agent-operator-toolkit/develop-from-specnpx skills add gabonio/agent-operator-toolkit --skill develop-from-specgit clone --depth 1 https://github.com/gabonio/agent-operator-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 | $0.00066 | $0.00466 |
| Opus 5 | $0.00033 | $0.00233 |
| Sonnet 5 | $0.00013 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
develop-from-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 — 25 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Develop from Spec
Workflow
- Discover. Read local instructions, relevant architecture/design documents, neighboring code and tests, build/delivery rules, and sources of truth. Load only matching references and lenses.
- Specify. Follow the repository's document convention. If none exists, propose
docs/specs/YYYY-MM-DD-<feature>-design.md. Use the specification workflow and the template. - Approve the specification. For large or high-risk work, stop for this approval before writing the implementation plan.
- Plan. Follow the repository convention or propose
docs/plans/YYYY-MM-DD-<feature>-implementation.md. Use the plan template. Make it literal enough for a faster executor without duplicating the specification. - Approve the plan. Stop before implementation until the user unambiguously approves. Bounded features may receive combined specification-and-plan approval.
- Execute. Follow ordered checkboxes, preserve unrelated work, make the smallest approved change, and record evidence. Ask for renewed approval on material drift.
- Verify. Run focused checks while iterating and the closest local production-like build before PR readiness. Report exact evidence and unresolved risk.
Material drift
Stop for renewed approval before changing scope, acceptance criteria, architecture, public behavior, data/API contracts, dependencies, security or authorization boundaries, migrations, or deployment behavior. Small implementation details may change when they preserve the approved design; record meaningful deviations.
Executor handoff
The implementation plan is the handoff. Do not create a third summary. The executor follows concrete decisions, contracts, constraints, tests, stop conditions, and commands—not persona prompts or lens names. Recommend planning and execution capabilities using model profiles, not a permanently pinned model name.
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.
- 2d ago First seen · 25 lines · 66 tokens per session scan A e367e0c0cc03
develop-from-spec is a skill published in the GitHub repository gabonio/agent-operator-toolkit (1 stars, last pushed 28d ago), licensed MIT. It adds 66 tokens to every session and 466 once invoked, about $0.0003 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.
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…