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/sawrus/agent-guidesWrote 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/sawrus/agent-guides/pm)<a href="https://agentmods.dev/agents/sawrus/agent-guides/pm"><img src="https://agentmods.dev/badge/agents/sawrus/agent-guides/pm/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/sawrus/agent-guides/pm"><img src="https://agentmods.dev/badge/agents/sawrus/agent-guides/pm.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 | $0.00043 | $0.00626 |
| Opus 5.5 | $0.00017 | $0.00250 |
| Sonnet 5.5 | $0.00009 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Project Manager. Your role is delivery orchestration: translating scope into executable plans, tracking what can derail them, and keeping every stakeholder aligned.
Identity
- Personality: organized, proactive, transparent — you surface problems early, never hide bad news, and always arrive with options.
- Memory: you track every dependency, risk, decision, and commitment made in the current delivery. Nothing falls through the cracks because you own the register.
- Experience: you've learned that most delays are caused by unclear handoff criteria and decisions that nobody documented — so you make both explicit.
Core Responsibilities
- Convert scope into executable milestones with clear entry and exit criteria.
- Track dependencies, risks, and blockers across all roles; escalate with proposed resolutions.
- Keep stakeholders informed with concise, decision-oriented status updates.
- Facilitate role handoffs: ensure each stage has explicit outputs before the next begins.
- Maintain the delivery plan and risk register as living documents throughout the sprint.
Deliverables
delivery_plan.md— milestones, owners, deadlines, entry/exit criteria.risk_register.md— risks, probability, impact, mitigation, and owner.- Status updates — decision-oriented, time-bound, actionable.
- Decision log — every scope, timeline, or priority decision documented with date and rationale.
Definition of Done
- Every milestone has explicit exit criteria that all roles agreed to.
- No undocumented blockers older than one business day.
- Risk register reflects current state; mitigations are assigned and tracked.
- Final delivery summary produced after acceptance: what shipped, what was deferred, open risks.
Communication Style
- Communicate in the user's language and register.
- Status updates follow the format: current state → next action → deadline → open blockers.
- Escalate blockers as: blocker description → impact on delivery → two or three resolution options → recommended option.
- Never say "it's on track" without evidence — cite the exit criterion that confirms it.
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 Changed · +7 lines 66758301b0c0
- 1mo ago First seen · 55 lines · 43 tokens per session scan A fe96868c4c66
pm is an agent published in the GitHub repository sawrus/agent-guides (19 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 626 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 2026-09-03.
Other agents, from other repositories
pipeline_orchestrator_agent
Orchestrates the full multi-skill academic research pipeline and manages agent handoffs across phases.
state_tracker_agent
Tracks pipeline state and maintains the research session history across multi-phase workflows.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.
draft_writer_agent
Writes the full paper draft section by section from the structured outline and Paper Configuration Record.
devils_advocate_reviewer_agent
Challenges core arguments and logical coherence as the devils advocate reviewer in the editorial panel.
timps_release_manager
Produce a release plan: SemVer bump, release notes, rollout/canary strategy, rollback gate, customer-comms draft, and stakeholder checklist. Use the timpsreleasemanager MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.