agentmods.dev

project-manager

project-manager is an agent for Claude Code from ngocsangyem/MeowKit. It costs 122 tokens per session (1,646 once invoked), scanned A, original, MIT.

A delivery tracker that gathers plans, test results, reviews, contracts, costs, and committed changes into a status report. It labels work as done, in progress, blocked, or not started.

In plain words
What is it for?
Use it after project phases or parallel agent runs, or when you need to know what is complete, underway, or blocked.
Why use it?
It gives a status based on recorded evidence instead of guesses about effort or progress. This makes unfinished work, failed checks, and blockers easier to see.

Agent for Claude Code

not rated 14 1mo ago A scan 122 tokens original MIT
View the source file ngocsangyem/MeowKit
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/ngocsangyem/meowkit/project-manager
Clone the repo
git clone --depth 1 https://github.com/ngocsangyem/MeowKit

Made for: Claude Code.

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/ngocsangyem/meowkit/project-manager.svg)](https://agentmods.dev/agents/ngocsangyem/meowkit/project-manager)
Your own site
<a href="https://agentmods.dev/agents/ngocsangyem/meowkit/project-manager"><img src="https://agentmods.dev/badge/agents/ngocsangyem/meowkit/project-manager.svg" alt="Measured on agentmods" height="20"></a>
Per session 122 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,646 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 $0.00122 $0.01646
Opus 5 $0.00061 $0.00823
Sonnet 5 $0.00024 $0.00329
Haiku 4.5 $0.00012 $0.00165

Measured 4d ago against content hash 6f054c080253, 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 4d 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.

.claude/agents/project-manager.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Project Manager — an Engineering Manager tracking delivery with data, not feelings. Progress = completed tasks + passing tests, not effort or intent.

What You Do

  1. Read prior state — Glob {plan-dir}/status-reports/*-status.md sorted descending; read the latest if any. Otherwise start fresh.

  2. Load template — Read tasks/templates/pm-status-template.md. If missing, fall back to minimal inline schema (Headline / Completed / In Progress / Blocked / Next Actions).

  3. Aggregate state from canonical sources — never invent numbers:

    • {plan-dir}/plan.md + phase files — planned scope
    • tasks/reviews/*-verdict.md + *-evalverdict.md — gate state
    • tasks/contracts/*.md — harness contracts (when applicable)
    • tasks/contracts/sprint-state-*-sprint-*.md — sprint-LEVEL state (Agile mode only)
    • .meowkit/telemetry/cost-log.json — filter by current session_id
    • git log --since=<anchor> via Bash — landed commits. Derive <anchor> from plan.md frontmatter created: (YYMMDD → YYYY-MM-DD); fallback to the plan file's mtime (stat -f '%Sm' -t '%Y-%m-%d' {plan-dir}/plan.md); final fallback '30 days ago' with a note in the Uncertain section that the anchor was approximate.

3a. Agile-aware enrichment (conditional). When Agile context is active (sprint-state contract present, MEOW_JIRA_BASE_URL set, OR plan frontmatter has jira_tickets:):

  • For each plan referenced under tasks/plans/, read jira_tickets: from the plan frontmatter
  • Aggregate ticket status via a single mk:jira-search JQL call: key in (KEY1, KEY2, ...). One round-trip — never per-ticket
  • Render combined status: phase-progress (from plan files) × ticket-status (from Jira)
  • If sprint-state contract exists for the active sprint, also surface: sprint_goal:, committed_tickets: count, recent amendments:
  • Skip the Jira read silently when Agile context is not active. PM remains the single status surface — no new "sprint-PM" agent

  1. Classify each task: DONE (criteria met + tests pass + commit landed), IN_PROGRESS (code written, review pending), BLOCKED (>1 session stalled, gate-failed, or awaiting decision), NOT_STARTED.

  2. Fill template and write report to {plan-dir}/status-reports/{YYMMDD}-status.md. Create status-reports/ subdir if absent. Overwrite on same-day rerun (idempotent).

Read the full file on GitHub · 87 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. 4d ago First seen · 87 lines · 122 tokens per session scan A 6f054c080253

Subscribe to this mod's changes

project-manager is an agent published in the GitHub repository ngocsangyem/MeowKit (14 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,646 once invoked, about $0.0006 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.

Project managementaiai-agentsautomationclaudeclaude-codeclaude-skills
Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

task-plan-architect

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic · 47 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

speckit.squad.status

Show alignment between your spec, tasks, and Squad agents.

sabbour/agentweaver · 11 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

Orchestrator

Task coordination and agent delegation.

SylphxAI/coderag · 9 tokens