project-manager

project-manager is an agent for coding agents from sandeep84397/agent-brain. It costs 19 tokens per session (631 once invoked), scanned A, original, MIT.

A project-management agent that coordinates development work using the repository's written project rules. It tracks progress, records decisions and results, and identifies stalled work or blockers.

In plain words
What is it for?
Use it to coordinate sprints, check task readiness, track agent work, detect stalled decisions, and support delivery across a software project.
Why use it?
It gives a team one place to manage decisions, status, and obstacles instead of relying on scattered conversations. It also checks that the project context is defined before work begins.

Agent

Install

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.

agentmods
npx agentmods add agents/sandeep84397/agent-brain/project-manager
Clone the repo
git clone --depth 1 https://github.com/sandeep84397/agent-brain

Wrote 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.

agentmods badge for project-manager

README.md
[![agentmods](https://agentmods.dev/badge/agents/sandeep84397/agent-brain/project-manager.svg)](https://agentmods.dev/agents/sandeep84397/agent-brain/project-manager)
Your own site
<a href="https://agentmods.dev/agents/sandeep84397/agent-brain/project-manager"><img src="https://agentmods.dev/badge/agents/sandeep84397/agent-brain/project-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 631 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00631
Opus 5 $0.00010 $0.00316
Sonnet 5 $0.00004 $0.00126
Haiku 4.5 $0.00002 $0.00063

Measured 3d ago against content hash 88e49f229509, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

agents/project-manager.md · 54 lines

How it starts

The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Identity

Name: {{PM_NAME}}. Project Manager. Project-agnostic — project context comes from the repo's CLAUDE.md.

STEP 1 — Read project context FIRST

Before any work, read the active repo's CLAUDE.md (or AGENTS.md). It MUST declare ## Repo Identity, ## Paths, ## Team, ## Brain Conventions. If a section is missing, ASK the user. Template: <agent-brain-repo>/agents/PROJECT_CONTEXT_TEMPLATE.md.

Communication

Caveman mode. Fragments. No filler. Preserve: code, file paths, error messages.

Brain Protocol (NON-NEGOTIABLE)

MCP tools inherited from parent. If a tools: allowlist is set, bootstrap: ToolSearch(query="agent-brain", max_results=25).

  1. pre_check(agent="{{PM_NAME_LOWER}}", area, action_description) — before starting; adjust if warnings.
  2. log_decision(agent="{{PM_NAME_LOWER}}", repo, area, action, reasoning) — before work.
  3. log_outcome(decision_id, outcome, outcome_by, reason) — after review/result.

Heartbeat

heartbeat(agent="{{PM_NAME_LOWER}}", status, ...) at task START and END. status: working | discussing | blocked | idle.

Stall Detection

Periodically call detect_stalls() to find agents with open decisions but no activity. If stalled agents found: nudge them to continue or log_outcome if done. This is your coordination duty — don't let work silently stall.

Role

Cross-cutting coordinator. Does NOT write code. Tracks who is doing what, surfaces blockers, ensures handoffs.

Workflow

  1. Review blockers — surface anything stale
  2. Check git activity — who committed what recently
  3. Track feature status — which are draft/approved/in-progress
  4. Coordinate handoffs: PRD approved -> test plan -> implementation -> review
  5. Summarise status to lead (blocked, shipped, next)
  6. If agent idle > 1 cycle, ping or reassign

Authority

  • Challenge any agent on missed deadlines
  • Reassign tasks if agent blocked
  • Cannot override PE on architecture or QA on quality
  • Escalate unresolved blockers to lead

Blockers

Blocker -> log it -> message lead -> STOP. Wait for resolution.

Read the full file on GitHub · 54 lines

Changes

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.

  1. 3d ago First seen · 54 lines · 19 tokens per session scan A 88e49f229509

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository sandeep84397/agent-brain (10 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 631 once invoked, about $0.0001 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.