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/codagent-ai/agent-skills/initnpx skills add Codagent-AI/agent-skills --skill initgit clone --depth 1 https://github.com/Codagent-AI/agent-skillsWhat 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 | $0.00040 | $0.00617 |
| Opus 5 | $0.00020 | $0.00309 |
| Sonnet 5 | $0.00008 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
init scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init
Set up Agent Skills in the current project. This skill is idempotent — safe to re-run.
Announce at start: "Initializing Agent Skills in this project."
Steps
1. Check Prerequisites
Check that the Agent Validator CLI is installed. If missing, tell the user what to install and stop.
agent-validator— runagent-validator --version.- If not found: "Agent Validator CLI is required. Install with
npm install -g agent-validator, then runagent-validator initin your project, then re-run/codagent:init." - If found, extract the version number and verify it is ≥ 0.15. If too old: "agent-validator 0.15 or higher is required (found <version>). Upgrade with
npm install -g agent-validator@latest, then re-run/codagent:init."
- If not found: "Agent Validator CLI is required. Install with
Use this shell snippet to compare versions:
version_gte() { [ "$(printf '%s\n' "$2" "$1" | sort -V | head -1)" = "$2" ]; }
Example: version_gte "$installed_version" "0.15" returns true if $installed_version ≥ 0.15.
If the CLI is missing or out of date, stop. The user must resolve it first, then resume /codagent:init.
Validator config (check after CLI passes):
.validator/config.ymlmust exist. If not found: "Validator config not found. Runagent-validator initin your project first, then re-run/codagent:init." Stop.
2. Print Success
Print a summary:
Agent Skills initialized successfully.
Available skills:
- /codagent:propose — evaluate an idea and write a proposal
- /codagent:spec — interview-driven requirement discovery
- /codagent:design — brainstorm architecture and write a design doc
- /codagent:test-plan — plan automated and acceptance testing
- /codagent:plan-tasks — break a change into scoped task files
- /codagent:implement-and-validate — implement a single task and verify with the validator
- /codagent:finalize-pr — push PR, wait for CI, fix failures
3. Commit
Invoke /agent-validator:validator-commit skip to commit any scaffolding changes. Checks are skipped because init only writes boilerplate.
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 · 61 lines · 40 tokens per session scan A b6cd0bb8d6aa
init is a skill published in the GitHub repository Codagent-AI/agent-skills (30 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 617 once invoked, about $0.0002 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.
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…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…