semgrep

A static security scanner that checks source code against known patterns for bugs and risks, including injection, authentication gaps, exposed secrets, and dangerous APIs.

In plain words
What is it for?
Use it on a whole codebase or a code change, choosing rule sets for technologies or risks such as OWASP, secrets, TypeScript, or Node.js.
Why use it?
It provides a repeatable scan that can catch known problems before a security-sensitive change is merged, while a manual review handles less predictable issues.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/lftpadilla/agent-dev-kit/semgrep
Any agent
npx skills add LFTPadilla/agent-dev-kit --skill semgrep
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 479 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00062 $0.00479
Opus 5 $0.00031 $0.00239
Sonnet 5 $0.00012 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured 2d ago against content hash d699f295c132, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

semgrep 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.

plugins/dev-skills/skills/semgrep/SKILL.md · 47 lines

What it actually says

semgrep — static analysis / SAST

Pattern-based static analysis. Deterministic, fast, rule-driven — the complement to an LLM security review: semgrep never misses a known pattern, the LLM reasons about novel ones. Run both.

Run

semgrep --config auto                 # auto-select rules for the detected languages
semgrep --config p/typescript         # registry rule pack (TS)
semgrep --config p/javascript
semgrep --config p/owasp-top-ten      # OWASP Top 10 patterns
semgrep --config p/secrets            # hardcoded secrets
semgrep --config p/nodejs             # Node-specific
semgrep --config auto --json          # machine-readable for processing

Scope to a diff for speed:

semgrep --config auto $(git diff --name-only --diff-filter=ACM main)

Install: pipx install semgrep (or brew install semgrep). No global install? pipx run semgrep ....

How to use the output

  1. Pick rule packs by the code under review — p/owasp-top-ten + p/secrets for auth/payment surfaces; p/typescript for general correctness.
  2. Triage findings by severity. Confirm each against the real code — semgrep patterns can false-positive on guarded paths.
  3. For a PR, scan only the diff (above) to keep it fast.
  4. Report: rule id, file:line, why it matters, fix. Don't auto-apply on security code without confirmation.

Gotchas

  • --config auto phones the registry; for offline/CI pin explicit p/... packs.
  • Custom rules go in .semgrep.yml — but prefer registry packs first (YAGNI).
  • Pairs with the security-review skill: semgrep catches known patterns, the review reasons about the rest.
Changes

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.

  1. 2d ago First seen · 47 lines · 62 tokens per session scan A d699f295c132

Subscribe to this mod's changes

semgrep is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d ago), licensed MIT. It adds 62 tokens to every session and 479 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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.

obra/superpowers · 37 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

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.

microsoft/vscode · 62 tokens