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/nicelight/devrails-26/startnpx skills add nicelight/DevRails-26 --skill startgit clone --depth 1 https://github.com/nicelight/DevRails-26What 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 | $0.00644 |
| Opus 5 | $0.00010 | $0.00322 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
start 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start
What This Skill Is
start is the package-level entrypoint for starting DevRails in a target
repository. It does not bootstrap the target itself.
Do not confuse two related surfaces:
- Package/install surface: use the installer from an available external DevRails checkout to install runtime command skills or bootstrap the skeleton.
- Generated project command:
/startis the lightweight scenario router used after runtime skills are installed in the target repository.
The generated /start command is sourced from
skills/_shared/references/commands/start.md in this source repo and is
written into target .agents/skills/start/SKILL.md and
.claude/skills/start/SKILL.md by scripts/install-framework.mjs.
Non-Negotiables
- Do not create epics, features, implementation plans, or runnable task records without a clarified PRD/delta.
- Do not create
.memory-bank/commands/; runtime command skills are installed directly into.agents/skills/and.claude/skills/. - Do not assume ORCHESTRATOR role or spawn subagents. Follow the target
AGENTS.mdrole contract. - Do not use direct
npx skills add <source-repo>for this source-only fork. Usescripts/install-framework.mjsfrom an available external DevRails checkout; it prepares a temporary vendored copy. - Keep skeleton/bootstrap separate from product planning. A fresh skeleton has
empty
.memory-bank/tasks/index.jsonand noFT-000or product task records.
If .memory-bank/ Is Missing
Treat the current repository root as <target-repo> unless the operator
explicitly supplied another target. Accept <devrails-checkout> only when the
operator supplied it or its scripts/install-framework.mjs is already
verifiable at a known path. Never guess or invent <devrails-checkout>.
Explain that this route installs or updates the full DevRails runtime command set and creates the skeleton. Then return this external bootstrap command with both placeholders replaced by verified, shell-safe paths:
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 · 70 lines · 20 tokens per session scan A 02c851dbd243
start is a skill published in the GitHub repository nicelight/DevRails-26 (22 stars, last pushed 5d ago), licensed MIT. It adds 20 tokens to every session and 644 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…