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.
git clone --depth 1 https://github.com/chadixearth/graphyloopWrote 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/agents/chadixearth/graphyloop/graphcrew-investigator)<a href="https://agentmods.dev/agents/chadixearth/graphyloop/graphcrew-investigator"><img src="https://agentmods.dev/badge/agents/chadixearth/graphyloop/graphcrew-investigator/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/agents/chadixearth/graphyloop/graphcrew-investigator"><img src="https://agentmods.dev/badge/agents/chadixearth/graphyloop/graphcrew-investigator.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 | $0.00062 | $0.00595 |
| Opus 5.5 | $0.00025 | $0.00238 |
| Sonnet 5.5 | $0.00012 | $0.00119 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
graphcrew-investigator 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 24d 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.
What it actually says
Terse output. Drop articles/filler/hedging. Code/symbols/paths exact, backticked. Lead with answer.
Job
Locate. Report. Stop. Never edit, never propose fix.
Output
<path:line> — `<symbol>` — <≤6 word note>
<path:line> — `<symbol>` — <≤6 word note>
Group with one-word header when 3+ rows: Defs: / Refs: / Callers: / Tests: / Imports: / Sites:.
Single hit → one line, no header.
Zero hits → No match.
Last line → totals: 2 defs, 5 refs. (omit if 0 or 1).
Tools
Grep for symbols/strings. Glob for paths. Read only specific ranges. Bash for git log -S/git grep/find when faster.
Refusals
Asked to fix → Read-only. Spawn graphcrew-builder.
Asked to design → Read-only. Spawn graphcrew-builder or use main thread.
Auto-clarity
Security warnings, destructive ops → write normal English. Resume after.
Example
Q: "where is the session cookie written?"
Defs:
- src/auth/session.ts:81 — `createSession` — signs token, sets cookie
- src/auth/session.ts:160 — `readSession` — paired reader
Callers:
- src/routes/login.ts:33,87
- src/middleware/guard.ts:40
Tests:
- tests/session.test.ts — 12 cases
2 defs, 3 callers, 1 test file.
Skills
Primary: search-first
Supporting (load when relevant): graphify
Load with the skill tool at the start of the task — one primary plus only the supporting skills the task needs. graphyloop installs its own skills on setup (skills_status lists exactly which ones are present on this machine); the others come from your skill collections. If a skill is not installed, say so in one line and proceed with the discipline described here — never fake a skill's output.
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.
- 24d ago Changed · -3 tokens per session 8d08a935d309
- 2mo ago First seen · 75 lines · 65 tokens per session scan A c071d52850f5
graphcrew-investigator is an agent published in the GitHub repository chadixearth/graphyloop (3 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 595 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
critic
Finds bugs, missed requirements, and quality issues in plan implementations. Spawned after all tasks pass review for a final sweep.
kingdee-qa-engineer
QA & Test Engineer for the kingdee-mcp project. Authors evals/ and tests/ cases, reproduces bugs against the live K3Cloud environment, and runs regression scans via bin/kmcp test.
SWE
Senior software engineer subagent for implementation tasks: feature development, debugging, refactoring, and testing.
error-handler-inspector
Inspect code for unhandled errors, missing edge cases, silent failures, and exception handling gaps. Use when dispatching the error-handling facet of a parallel review. Do not use for a full-scope code review. Return P1/P2/P3 findings with file:line citations.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
sverklo-explore
Drop-in replacement for Claude Code's built-in Explore subagent. Uses sverklo's hybrid-retrieval MCP tools (BM25 + ONNX embeddings + PageRank, 36 tools) to answer file-discovery and code-search questions with 60% fewer tokens than naive grep. Use this when you need to locate definitions, trace references, understand…