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/backspace-shmackspace/claude-devkit/semgrepnpx skills add backspace-shmackspace/claude-devkit --skill semgrepgit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.00095 | $0.06569 |
| Opus 5 | $0.00048 | $0.03284 |
| Sonnet 5 | $0.00019 | $0.01314 |
| Haiku 4.5 | $0.00010 | $0.00657 |
Grade B, and why
semgrep scanned grade B with 1 finding 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.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
[ -n "[OUTPUT_DIR]" ] && rm -rf [OUTPUT_DIR]/repos Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 559 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semgrep Security Scan
Run a Semgrep scan with automatic language detection, parallel execution across language groups, and merged SARIF output.
Essential Principles
- Always use
--metrics=off— Semgrep sends telemetry by default;--config autoalso phones home. Everysemgrepcommand must include--metrics=offto prevent data leakage during security audits. - User must approve the scan plan (Step 3 is a hard gate) — The original "scan this codebase" request is NOT approval. Present exact rulesets, target, engine, and mode; wait for explicit "yes"/"proceed" before running scanners.
- Third-party rulesets are required, not optional — Trail of Bits, 0xdea, and Decurity rules catch vulnerabilities absent from the official registry. Include them whenever the detected language matches.
- Run all scan workers in parallel — Parallel execution is the core performance advantage. Do not run language scans strictly one-after-another when independence allows overlap.
- Always check for Semgrep Pro before scanning — Pro enables cross-file taint tracking and catches ~250% more true positives. Skipping the check means silently missing critical inter-file vulnerabilities.
When to Use
- Security audit of a codebase
- Finding vulnerabilities before code review
- Scanning for known bug patterns
- First-pass static analysis
When NOT to Use
- Binary analysis → Use binary analysis tools
- Already have Semgrep CI configured → Use existing pipeline
- Need cross-file analysis but no Pro license → Consider CodeQL as alternative
- Creating custom Semgrep rules → Use
semgrep-rule-creatorskill - Porting existing rules to other languages → Use
semgrep-rule-variant-creatorskill
Output Directory
All scan results, SARIF files, and temporary data are stored in a single output directory.
- If the user specifies an output directory in their prompt, use it as
OUTPUT_DIR. - If not specified, default to
./static_analysis_semgrep_1. If that already exists, increment to_2,_3, etc.
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 · 559 lines · 95 tokens per session scan B 3ad46fa0988f
semgrep is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 9d ago), licensed MIT. It adds 95 tokens to every session and 6,569 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
worktree-switching
Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-fresh-verifier
L4 blind fresh verifier - independently checks a candidate roadmap or plan against the exact mission and repository; APPROVE/REJECT, default-FAIL.
cron
Schedule reminders and recurring tasks.
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.