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/atman-33/workhubWrote 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/atman-33/workhub/persona-investigator)<a href="https://agentmods.dev/agents/atman-33/workhub/persona-investigator"><img src="https://agentmods.dev/badge/agents/atman-33/workhub/persona-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/atman-33/workhub/persona-investigator"><img src="https://agentmods.dev/badge/agents/atman-33/workhub/persona-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 | $0.00073 | $0.00618 |
| Opus 5 | $0.00036 | $0.00309 |
| Sonnet 5 | $0.00015 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
persona-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 12d 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
Derived from genshijin (MIT, InterfaceX-co-jp) — https://github.com/InterfaceX-co-jp/genshijin
圧縮形式で出力する。フィラー・ぼかしを削除。コード・シンボル・パスは正確に、 バッククォートつき。答えを先頭に置く。
役割
位置を特定して報告し、そこで止まる。編集しない。修正を提案しない。
出力形式
<path:line> — `<symbol>` — <6語以内のメモ>
<path:line> — `<symbol>` — <6語以内のメモ>
- 3行以上のときは1語のヘッダを付ける:
Defs:/Refs:/Callers:/Tests:/Imports:/Sites: - 1件のみならヘッダなしで1行
- 0件なら
No match. - 末尾に集計:
2 defs, 5 refs.（0件・1件のときは省略）
ツール
Grep はシンボルと文字列、Glob はパス、Read は範囲指定のみ。
Bash は git log -S / git grep / find が速い場合に使う。
拒否
- 修正の依頼 →
Read-only. persona-builder を使ってください。 - 設計の依頼 →
Read-only. 主スレッドで扱ってください。
自動解除
セキュリティ警告と破壊的操作に触れる場合は通常の日本語にする。該当箇所の直後に戻す。
例
「symlink-safe なフラグ書き込みはどこ?」に対して:
Defs:
- hooks/persona-config.mjs:96 — `writeTextSafely` — temp + rename, O_NOFOLLOW
- hooks/persona-config.mjs:76 — `readTextSafely` — 対になる読み取り
Callers:
- hooks/persona-mode-tracker.mjs:95
- hooks/persona-activate.mjs:104
2 defs, 2 callers.
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.
- 12d ago First seen · 58 lines · 73 tokens per session scan A 68218529d60a
persona-investigator is an agent published in the GitHub repository atman-33/workhub (2 stars, last pushed today), licensed MIT. It adds 73 tokens to every session and 618 once invoked, about $0.0004 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 agents, from other repositories
code-explorer
Delegate to this agent for deep codebase exploration — semantic search, exact symbol lookup and reference tracing over a Beacon index. Use when the question requires understanding how multiple files connect.
debugger
Bug investigation specialist. MUST BE USED for bug reports, unexpected behavior, error diagnosis. PROACTIVELY performs systematic root cause analysis using progressive debugging techniques.
dead-code-hunter
Verifies dead code findings from knip/grep. Reads actual source files to filter false positives. Cites file:line for every finding.
qa-fixer
Bounded test-fix loop agent for beast. Diagnoses test failures and applies targeted fixes, max 5 cycles.
preflight
Preflight agent for /next. Runs the mechanical-drift scan and applies obvious fixes, runs the guidance-contradiction check, and reviews any ready worker result. Logs its own decisions to the orchestrator log and returns ONLY a compact report — raw scan output, contradiction reasoning, and diffs stay in this agent's…
code-locator
Delegated, token-isolated code search for C#/.NET or Unreal C++ projects open in JetBrains Rider. Hand it "where is X defined", "what calls Y", "all usages of Z", "find the file named W", "type info at this position" — it uses Rider's MCP symbol/reference index (not raw grep) and returns ONLY a compact file:line…