security-triage

security-triage is a skill for Claude Code, Codex from flytohub/flyto-indexer. It costs 105 tokens per session (1,373 once invoked), scanned A, original, Apache-2.0.

A security-research workflow that narrows a large indexed codebase to a ranked list of code paths worth human investigation. It uses code search, dependency relationships, data-flow clues, complexity, change history, tests, and error handling.

In plain words
What is it for?
Use it to prioritize possible vulnerabilities, trace data to dangerous operations, assess affected code, and prepare evidence for a security researcher.
Why use it?
It focuses limited research time on the parts of a repository most likely to expose meaningful attack paths, without claiming that a vulnerability is confirmed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to prioritize possible vulnerabilities, trace data to dangerous operations, assess affected code, and prepare evidence for a security researcher.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flytohub/flyto-indexer/security-triage
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.

Any agent
npx skills add flytohub/flyto-indexer --skill security-triage
Clone the repo
git clone --depth 1 https://github.com/flytohub/flyto-indexer

Made for: Claude Code, 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 security-triage

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/flytohub/flyto-indexer/security-triage"><img src="https://agentmods.dev/badge/skills/flytohub/flyto-indexer/security-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,373 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.
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 $0.00105 $0.01373
Opus 5 $0.00053 $0.00687
Sonnet 5 $0.00021 $0.00275
Haiku 4.5 $0.00011 $0.00137

Measured 10d ago against content hash f327f26e8405, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

security-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 10d 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.

skills/security-triage/SKILL.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security research triage

A budget-aware funnel over the flyto-indexer MCP tools. It narrows a whole repository to the handful of code paths worth reading, spends expensive verification only on that handful, and hands the result to a human as an evidence package.

The intelligence is in the sequencing and the stop rules, not in any one tool. flyto-indexer stays a set of dumb, lean tools; this skill is the smart caller.

The output is a prioritized reading list, not a judgement. Every item says what evidence put it there and how strong that evidence is. A researcher decides what is real.

Tools this skill drives (all already in flyto-indexer — nothing new)

  • research_priority — the ranked candidate list (fuses taint reachability, sink severity, complexity, git churn, test gaps, error handling). CLI: flyto-index research-priority.
  • call_hierarchy — LSP-resolved call edges. Type-aware; expensive, so used only on the shortlist.
  • impact — references / blast radius / reachability of a symbol.
  • search, structure — context when a candidate needs it.

The funnel

Run the stages in order. Each stage narrows; cost rises. Stop as soon as a stage gives the researcher enough — do not run later stages out of habit.

Stage 0 — Is there an index?

If .flyto-index/ is missing, run flyto-index scan . once. Otherwise skip.

Stage 1 — Proven flows first (cheap, high confidence)

research_priority(project=<name>, top_n=20, include_unproven=false)

Proven source-to-sink flows are near-certain leads. If this returns any, they are the top of the reading list immediately — a proven flow outranks every unproven lead. If it returns enough for the researcher (say ≥ 5 strong ones), you may hand off now and skip the deeper stages.

Stage 2 — Ranked leads (the wide net, already fused)

research_priority(project=<name>, top_n=20)

The score already fuses git churn, complexity, test gaps and evidence tier — do not re-run those tools per candidate, read the reasons/signals the result already carries. Keep the top ~8 for Stage 3; the rest stay on the list below the shortlist.

Read the full file on GitHub · 126 lines

Files

What ships with it

2 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.

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. 10d ago First seen · 126 lines · 105 tokens per session scan A f327f26e8405

Subscribe to this mod's changes

security-triage is a skill published in the GitHub repository flytohub/flyto-indexer (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 105 tokens to every session and 1,373 once invoked, about $0.0005 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

weavatrix

Use the Weavatrix MCP when a repository task benefits from indexed evidence: codebase orientation, symbol/source search, dependency or call graphs, change impact, API/event tracing, architecture checks, Git/coverage evidence, duplicates, dead-code review, or semantic context. Skip it for trivial single-file edits or…

Weavatrix/weavatrix · 78 tokens

weavatrix

Use the Weavatrix MCP when a repository task benefits from indexed evidence: codebase orientation, symbol/source search, dependency or call graphs, change impact, API/event tracing, architecture checks, Git/coverage evidence, duplicates, dead-code review, or semantic context. Skip it for trivial single-file edits or…

Weavatrix/weavatrix · 78 tokens

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

memorix

Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.

AVIDS2/memorix · 34 tokens

memorix-mini-skills

Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.

AVIDS2/memorix · 30 tokens

memorix-orchestrate

Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.

AVIDS2/memorix · 37 tokens