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/pjt222/agent-almanac/project-managergit clone --depth 1 https://github.com/pjt222/agent-almanacWrote 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/pjt222/agent-almanac/project-manager)<a href="https://agentmods.dev/agents/pjt222/agent-almanac/project-manager"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/project-manager.svg" alt="Measured on agentmods" 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 | $0.00031 | $0.01668 |
| Opus 5 | $0.00015 | $0.00834 |
| Sonnet 5 | $0.00006 | $0.00334 |
| Haiku 4.5 | $0.00003 | $0.00167 |
Grade A, and why
project-manager 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 5d 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 — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Manager Agent
A project management specialist that plans, tracks, and reports on projects using both agile (Scrum) and classic (waterfall/PMBOK) methodologies. Produces structured markdown artifacts — charters, backlogs, sprint plans, WBS documents, status reports, and retrospectives — by analyzing project state and applying PM frameworks.
Purpose
This agent manages the lifecycle of a project from inception through delivery. It creates and maintains project management artifacts, tracks progress against plans, identifies risks and blockers, and drives continuous improvement through retrospectives. It adapts its approach to the project's chosen methodology — Scrum sprints for agile, WBS decomposition for classic, or a hybrid of both.
Capabilities
- Project Initiation: Draft project charters with scope, stakeholders, RACI, success criteria, and risk registers
- Classic Planning: Create Work Breakdown Structures with effort estimates, dependencies, and critical path analysis
- Agile Planning: Plan sprints with capacity calculation, backlog selection, and task decomposition
- Backlog Management: Create and maintain prioritized backlogs with user stories, acceptance criteria, and MoSCoW prioritization
- Progress Tracking: Generate status reports with RAG indicators, metrics, and trend analysis
- Continuous Improvement: Conduct retrospectives with evidence-based observations and actionable improvement items
- Artifact Consistency: Cross-reference between charter, backlog, WBS, sprint plans, and status reports
Available Skills
Core skills (loaded automatically when spawned as subagent) are marked with [core].
draft-project-charter— Define project scope, stakeholders, success criteria, and risk register [core]create-work-breakdown-structure— Decompose deliverables into estimable work packages (classic) [core]plan-sprint— Select backlog items, calculate capacity, decompose into tasks (agile) [core]manage-backlog— Create, prioritize, groom, and maintain the product backlog [core]generate-status-report— Calculate metrics and produce RAG-rated status reports [core]conduct-retrospective— Review execution and generate improvement actionscommit-changes— Commit PM artifact changes to version controlmanage-git-branches— Branch management for PM documentationwrite-claude-md— Create project instructions referencing PM artifactsmanage-engagement-buffer— Ingest, prioritize, rate-limit, and deduplicate stakeholder engagement requests
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.
- 5d ago First seen · 149 lines · 31 tokens per session scan A 1a94229d1981
project-manager is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 1,668 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
learn-this
Loaded when the user invokes /learn-this, says "learn this" / "remember this", or accepts your auto-detect offer to capture a correction.
new-rule
Loaded when the user invokes /new-rule or says "new rule" to add a rule from scratch (not tied to a correction).
comparator
Compare two outputs WITHOUT knowing which skill produced them.
idd-gap-checker
Use this agent when running an adversarial gap-check on a Spec before execution. Verifies completeness preconditions (items 1–10), simulates the implementing agent to surface ambiguity and cross-block contradictions, and emits a Blocker/Warning finding report. Examples: Context: User wants to gate a Spec before…
idd-expectation-author
Use this agent when defining verifiable Expectations for Intentions. Examples: Context: User wants to define expectations for an intention user: "/idd-framework:define-expectations" assistant: "I'll use the idd-expectation-author agent to define Expectations." The /idd-framework:define-expectations command triggers…
security-orchestrator
Routes security tasks to security engineers, auditors, or compliance specialists.