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 skills add capitalone/context-specs --skill env-initgit clone --depth 1 https://github.com/capitalone/context-specsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/capitalone/context-specs/env-init)<a href="https://agentmods.dev/skills/capitalone/context-specs/env-init"><img src="https://agentmods.dev/badge/skills/capitalone/context-specs/env-init/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/capitalone/context-specs/env-init"><img src="https://agentmods.dev/badge/skills/capitalone/context-specs/env-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00112 | $0.03735 |
| Opus 5.5 | $0.00045 | $0.01494 |
| Sonnet 5.5 | $0.00022 | $0.00747 |
| Haiku 4.5 | $0.00011 | $0.00374 |
Grade A, and why
env-init 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 1mo 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 — 295 lines — stays where its author put it; the contents beside it link to each section on GitHub.
env-init
Stand up a project as a harness environment. You are an autonomous
installer: you write the artifacts end-to-end, explain the significance of
each as you go, and gather everything onto a feature/env-init PR the human
reviews and merges.
You are the second half of a two-command setup, and the split is the point — it is harness engineering in miniature:
context-specs add <path>already ran (deterministic CLI, tier 1): it registered this environment with the harness repo, symlinked the canonical skills/agents into.claude/(gitignored), and wrote the managed.gitignoreblock. Everything a script can do without reading the project, a script did.- You do what needs judgment (Software 3.0, tier 2): every artifact below requires reading this project — its manifests, README, CI, conventions. Scan, generate, cite the evidence. Never invent a command you didn't see evidence for — ask instead.
The tier test, if you're ever unsure what belongs to you: could this be written without reading the project's code? Yes → it's the CLI's/harness repo's, leave it alone. No → it's yours to generate here.
Operating mode
Run the steps end-to-end without stopping for per-step approval — the user
reviews everything in the feature/env-init PR. Your job while installing is
to explain significance: for each artifact, one or two sentences on what it
is, why it exists, and what would break without it. Lead with the why, then
write the file.
Read first: references/mental-model.md (so you can explain what the harness
is) and references/invariants-to-preserve.md (the rules nothing you
generate may break). Load other references as each step needs them.
Stop-and-confirm points — the only interruptions:
- Secret-copying (bootstrap step) — before writing any
cpline that touches a.envor credentials file: name the exact files, confirm copy direction (source → worktree, never reverse, never delete), get explicit consent. - Reviewer choice — wires CI and billing; the user's call.
- The PR merge — after the PR opens, stop and wait for the human.
What ships with it
16 files 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.
- assets/AGENTS.md.template 5.0 KB
- assets/bootstrap-worktree.template.sh 1.8 KB runs code
- assets/expert-skeleton/references/README.md 249 B
- assets/expert-skeleton/SKILL.md 3.5 KB
- assets/harness-env.template 2.0 KB
- assets/REVIEW.md 2.4 KB
- assets/workflows/claude-review.yml 3.2 KB
- references/agents-md-guidance.md 3.4 KB
- references/config-options.md 6.4 KB
- references/dispatcher-explained.md 16 KB
- references/invariants-to-preserve.md 4.1 KB
- references/local-checks-design.md 11 KB
- references/mental-model.md 7.3 KB
- references/project-discovery.md 4.5 KB
- references/reviewer-options.md 5.9 KB
- references/worktree-bootstrap.md 4.7 KB
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.
- 1mo ago First seen · 295 lines · 112 tokens per session scan A e7d35799c07c
env-init is a skill published in the GitHub repository capitalone/context-specs (44 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 3,735 once invoked, about $0.0004 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…