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 Obsidian-Owl/specwright --skill gate-securitygit clone --depth 1 https://github.com/Obsidian-Owl/specwrightWrote 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/obsidian-owl/specwright/gate-security)<a href="https://agentmods.dev/skills/obsidian-owl/specwright/gate-security"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/gate-security/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/obsidian-owl/specwright/gate-security"><img src="https://agentmods.dev/badge/skills/obsidian-owl/specwright/gate-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00038 | $0.00730 |
| Opus 5.5 | $0.00015 | $0.00292 |
| Sonnet 5.5 | $0.00008 | $0.00146 |
| Haiku 4.5 | $0.00004 | $0.00073 |
Grade B, and why
gate-security 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 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.
Enumerates the file system for secretsmediumData exfiltration
Searching home directories for .env, .ssh, .aws or credential files is reconnaissance for credential theft.
- Scan for .env files, credential files, or key files staged for commit. 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gate: Security
Goal
Ensure the codebase doesn't leak secrets, introduce injection vulnerabilities, or expose sensitive data. Use real security tooling when available. Use LLM judgment for analysis that tools can't do.
Inputs
{projectArtifactsRoot}/config.json--commands.lint, SAST tool config if available{repoStateRoot}/work/{selectedWork.id}/workflow.json-- selected work unit- Changed files (detected via
git diff)
Outputs
- Evidence file at
{workDir}/evidence/security-report.md - Gate status in the selected work's
workflow.json - Findings shown inline with severity, location, and remediation
Constraints
Scope (MEDIUM freedom):
- Focus on changed files. Use
git diff --name-onlyagainst main branch. - If no changed files detected, check all files in work scope.
Phase 1 — Detection (LOW freedom, BLOCK severity):
- Scan for secrets: API keys, tokens, passwords, private keys in source files.
- Scan for .env files, credential files, or key files staged for commit.
- Check .gitignore covers sensitive patterns.
- If a configured SAST tool exists (e.g.,
semgrep,eslint-plugin-security), run it. - Any secret or credential found = BLOCK finding.
Phase 2 — Analysis (HIGH freedom, WARN severity):
- Review changed code for injection patterns (SQL, command, XSS, path traversal).
- Check that external data is treated as untrusted (per Constitution security practices).
- Check that authentication/authorization patterns aren't weakened (per Constitution auth/authz practices).
- Findings are WARN unless clearly exploitable (then BLOCK).
Phase 3 — Logical security (HIGH freedom, WARN severity):
- Missing authentication (CWE-306): mutation-capable handler functions (HTTP routes, gRPC handlers, GraphQL resolvers) performing state-changing operations without any visible auth check. Only flag when auth is completely absent. Skip if no mutation-capable handler patterns detected in changed files.
- For code-level error handling analysis (CWE-636, CWE-209), defer to gate-semantic which owns those categories with tiered tooling.
- All Phase 3 findings are WARN. Never BLOCK.
- Phase 3 focuses on logical control-flow; defer to Phase 2 when a finding is already captured as an injection pattern.
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 · 79 lines · 38 tokens per session scan B 85db0e6fd992
gate-security is a skill published in the GitHub repository Obsidian-Owl/specwright (10 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 730 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (enumerates the file system for secrets). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
rust-skills
Rust best practices — 179 rules across 14 categories for idiomatic, optimized Rust code.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
llm-friendly-context
Clarifies inputs, outputs, success criteria, decisions, and unresolved conditions so downstream consumers can execute without guessing. Use when writing or revising LLM-facing prompts, handoffs, planning artifacts, reviews, reports, or generated instructions.
import-spec
Imports a spec-kit feature spec into Shipyard in place of brainstorming. Use when a spec-kit feature directory with spec.md exists.
shipyard-ship
Use when delivering or releasing a completed Shipyard phase under Codex — final verification, pre-ship security audit, documentation, and release. Trigger when the user says "ship it", "ship this phase", "release this", "we're done — finalize", or "run the shipyard ship workflow". This is the Codex inline-sequential…
brainstorm
Explores a codebase, researches the problem space, and produces an approved design specification before any code is written. Use when the user wants to create a new feature, add significant functionality, redesign a subsystem, or build something that touches multiple parts of the project.