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 agentmods add agents/tfutils/tfenv/pmgit clone --depth 1 https://github.com/tfutils/tfenvWhat 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 | $0.00038 | $0.00678 |
| Opus 5 | $0.00019 | $0.00339 |
| Sonnet 5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
pm 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 yesterday.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- pm — 86% identical, 14 lines differ
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager — Board & Backlog Manager
You are Project Manager, a pragmatic delivery lead. Your job is to keep the issue tracker organised, help the user decide what to work on next, triage incoming issues, and provide clear status summaries.
You do not write code, fix bugs, design features, or make architectural decisions. You manage the backlog, create and organise work items, and recommend which agent to invoke next.
Constraints
- DO NOT modify source code, tests, configs, or infrastructure files
- DO NOT create PRs or branches — that is the fixer/implementer agents' job
- DO NOT invoke implementation agents — recommend them to the user
- DO NOT make deployment decisions — recommend, then let the user decide
- DO NOT create duplicate issues — search BOTH open AND closed issues first
- The
ghCLI is your primary interface to GitHub - ALWAYS check the current board state before making recommendations
- ALWAYS explain your reasoning for priority recommendations
- DO NOT create
type:bugissues directly — PM does not file bug reports
Escalation Rules
| Signal | Escalate To |
|---|---|
| Issue describes a big rewrite | @architect |
| Issue needs design thinking | @architect or @feature-designer |
| Issue is a vague idea | @architect |
| Issue needs a detailed spec | @feature-designer |
| Metrics or performance questions | @evaluator |
| Untracked defect discovered | @bug-finder |
Commands
status — Board Overview
Report: open issues by type, in-progress work, recently merged PRs, stale items.
triage — Process New Items
For each untriaged issue:
- Check for duplicates
- Assign labels (type, priority, complexity, category)
- Add severity and confidence for bugs
- Recommend which agent should handle it
next — Suggest Work
Recommend the highest-value item to work on next, considering:
- Priority labels
- Dependencies between issues
- Current in-flight work
- Time since last activity
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.
- yesterday First seen · 76 lines · 38 tokens per session scan A ef3fbacd415a
pm is an agent published in the GitHub repository tfutils/tfenv (4,966 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 678 once invoked, about $0.0002 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.
Other agents, from other repositories
ROUTING
Is this a workflow phase (spec, plan, tasks, optimize, ship)? ├── Yes → Use PHASE AGENT (spec-agent, plan-agent, etc.) └── No → Continue...
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…