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/codacy/codacy-skills/codacy-analysis-clinpx skills add codacy/codacy-skills --skill codacy-analysis-cligit clone --depth 1 https://github.com/codacy/codacy-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 | $0.00122 | $0.04119 |
| Opus 5 | $0.00061 | $0.02060 |
| Sonnet 5 | $0.00024 | $0.00824 |
| Haiku 4.5 | $0.00012 | $0.00412 |
Grade A, and why
codacy-analysis-cli 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 — 460 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codacy Analysis CLI
Glossary: See glossary.md for shared definitions of Codacy concepts (issues, findings, severity, coverage, tools, patterns, etc.).
The Codacy Analysis CLI (codacy-analysis) runs static analysis locally on a repository. It detects languages, selects tools, and reports issues — without pushing code to Codacy. This is a different tool from the Codacy Cloud CLI (codacy), which queries remote Codacy data.
Always use --output-format json for structured output in agentic workflows.
Setup
# Install
npm i -g @codacy/analysis-cli
# Verify
codacy-analysis --help
Authentication (optional)
Authentication is only required for init --remote (fetching config from a Codacy repository). Local analysis works without authentication.
# Option 1: Interactive login
codacy-analysis login
# Option 2: Token flag
codacy-analysis login --token <your-api-token>
# Option 3: Environment variable
export CODACY_API_TOKEN=<your-api-token>
# Obtain tokens: Codacy > My Account > Access Management
# Remove credentials
codacy-analysis logout
Shared session: The Analysis CLI and the Cloud CLI (codacy) share the same credentials at ~/.codacy/credentials. Logging in or out with either CLI applies to both — there is no need to authenticate separately.
Getting help
codacy-analysis --help
codacy-analysis <command> --help
# e.g. codacy-analysis analyze --help
Filesystem conventions
The CLI uses two managed locations:
| Location | Scope | Contents |
|---|---|---|
.codacy/ (in repo root) |
Per-project | codacy.config.json, generated/ (tool configs), .gitignore (auto-created) |
~/.codacy/ (home dir) |
Machine-wide | Runtimes, tool binaries, caches, logs, credentials |
The analyzed repository is never modified outside of .codacy/. The .codacy/.gitignore is auto-created to exclude generated/, logs, and other transient files.
Key files
What ships with it
3 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.
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 · 460 lines · 122 tokens per session scan A 79e484144eac
codacy-analysis-cli is a skill published in the GitHub repository codacy/codacy-skills (11 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 4,119 once invoked, about $0.0006 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…