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 flytohub/flyto-indexer --skill security-triagegit clone --depth 1 https://github.com/flytohub/flyto-indexerWrote 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/flytohub/flyto-indexer/security-triage)<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.
<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>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 | $0.00105 | $0.01373 |
| Opus 5 | $0.00053 | $0.00687 |
| Sonnet 5 | $0.00021 | $0.00275 |
| Haiku 4.5 | $0.00011 | $0.00137 |
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.
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.
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.
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.
- 10d ago First seen · 126 lines · 105 tokens per session scan A f327f26e8405
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.
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
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…
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…
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.