mantishack: Skill for Codex

.codex/skills/semgrep-triage/SKILL.md

semgrep-triage is a skill for Codex from deonmenezes/mantishack. It costs 29 tokens per session (282 once invoked), scanned A, original, Apache-2.0.

A security-testing guide for running Semgrep, a tool that scans source code for possible vulnerabilities, and sorting its results into candidate, confirmed, or rejected findings.

In plain words
What is it for?
Use it to scan a file or directory with Semgrep and investigate the reported candidates. It covers choosing scan rules, tracing source-to-sink paths, validating reachable issues, and reporting when Semgrep is unavailable.
Why use it?
A scanner result is only a possible issue, not proof of a vulnerability. This process requires checking whether attacker-controlled data can actually reach the risky code before reporting a finding.

Skill for Codex

Written for Codex: installed under .codex/.

This is deonmenezes/mantishack's own configuration. It tells Codex how to work on mantishack itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mantishack configures →

Reuse

Borrowing it

Nothing to install: this file belongs to deonmenezes/mantishack. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/deonmenezes/mantishack/main/.codex/skills/semgrep-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/deonmenezes/mantishack

Made for: Codex.

Wrote 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.

agentmods badge for semgrep-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/deonmenezes/mantishack/semgrep-triage/github.svg)](https://agentmods.dev/skills/deonmenezes/mantishack/semgrep-triage)
Your own site
<a href="https://agentmods.dev/skills/deonmenezes/mantishack/semgrep-triage"><img src="https://agentmods.dev/badge/skills/deonmenezes/mantishack/semgrep-triage/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.

agentmods 80×15 button for semgrep-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/deonmenezes/mantishack/semgrep-triage"><img src="https://agentmods.dev/badge/skills/deonmenezes/mantishack/semgrep-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 282 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00029 $0.00282
Opus 5 $0.00015 $0.00141
Sonnet 5 $0.00006 $0.00056
Haiku 4.5 $0.00003 $0.00028

Measured 11d ago against content hash 4e32309b4d77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

semgrep-triage 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 11d 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.

.codex/skills/semgrep-triage/SKILL.md · 13 lines

What it actually says

Use the semgrep_scan tool (mantis_semgrep MCP server) for the Detect stage of the Mantis pipeline: high-recall SAST over a file or directory.

  • Default config to "auto". Prefer a narrower ruleset (e.g. "p/owasp-top-ten", "p/secrets") when you already know the vulnerability class you're hunting.
  • Every result is a candidate, not a finding. Do not report severity from semgrep's own ERROR/WARNING/INFO labels as final severity -- those describe rule confidence, not demonstrated impact.
  • For each candidate: trace the exact source-to-sink path in the surrounding code before deciding it's worth validating further. If the sink is unreachable from attacker-controlled input (auth-gated, admin-only, framework-sanitized), reject it and cite the specific roadblock -- never "seems safe."
  • Reachable candidates move to attacker-simulation validation (see program-analysis skill for the reachability tools) before you claim a confirmed finding.
  • If semgrep reports available: false, tell the user it isn't installed rather than silently skipping SAST coverage.
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. 11d ago First seen · 13 lines · 29 tokens per session scan A 4e32309b4d77

Subscribe to this mod's changes

semgrep-triage is a skill published in the GitHub repository deonmenezes/mantishack (495 stars, last pushed 29d ago), licensed Apache-2.0. It adds 29 tokens to every session and 282 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

compare-harnesses

Diff two scaffolded harnesses (ADR-031). Reports manifest meta drift + host list + per-file fingerprint changes (added/removed/changed). Exits 0 IDENTICAL, 1 DRIFT, 2 missing manifest. Use --bundle for the ADR-031 schema-1 JSON envelope.

ruvnet/metaharness · 66 tokens

create-harness

Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a…

ruvnet/metaharness · 89 tokens

diag-harness

Kernel-version skew check (ADR-027). Reports manifest surface + manifest kernel + installed kernel + verdict (match/patch-diff/minor-diff/major-diff). Exits 1 on minor/major skew with a copy-pasteable npm install @metaharness/[email protected] next step. Exits 2 if no .harness/manifest.json at path.

ruvnet/metaharness · 85 tokens

oia-manifest

Emit .harness/oia-manifest.json declaring layer alignment with the OIA v0.1 9-layer reference architecture. Self-describes the harness's MCP wiring, witness signing, audit log, identity posture (always 'none' at v0.1). --check verifies an existing manifest, --dry-run prints without writing, --json emits to stdout.

ruvnet/metaharness · 79 tokens

repo-genome

7-section readiness scorecard for a LOCAL repo. Reports repo type + agent topology + MCP risk + test confidence + release readiness + recommended harness plan + scorecard. Exit 0 ready, 1 needs-work, 2 blocked. --json for the 6-field scorecard, --bundle for the ADR-031 schema-1 envelope.

ruvnet/metaharness · 73 tokens

example-harness

Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…

ruvnet/metaharness · 90 tokens