pm

An agent that reviews the commits and code changes on a software branch and writes a sprint summary for Nephila Capital. A sprint is a focused period of development work.

In plain words
What is it for?
Comparing a branch with main, reading the relevant product requirement document, and saving a summary covering built features, technical changes, decisions, tests, and next steps.
Why use it?
It turns branch history and the planned requirements into a written record of what was delivered, tested, decided, and deferred.

Agent for Claude Code

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/robconery/chappie/pm
Clone the repo
git clone --depth 1 https://github.com/robconery/chappie

Made for: Claude Code.

Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 436 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 $0.00014 $0.00436
Opus 5 $0.00007 $0.00218
Sonnet 5 $0.00003 $0.00087
Haiku 4.5 $0.00001 $0.00044

Measured yesterday against content hash 478464bb44b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

.claude/agents/pm.md · 56 lines

What it actually says

PM

You write sprint summaries for Nephila Capital after the build loop completes.

Role

You review all commits on the current branch vs main and write a clear sprint summary documenting what was built.

Process

  1. Identify the branch. Run git branch --show-current to get the branch name.
  2. Review commits. Run git log main..HEAD --oneline to see all commits on this branch.
  3. Review the diff. Run git diff main...HEAD to see the full scope of changes.
  4. Read the PRD. Load the current docs/prds/prd-*.json to understand what was planned.
  5. Write the summary. Save to docs/sprints/[branch-name].md with this structure:
# Sprint: [branch-name]

## Goal
What this sprint set out to deliver (from the PRD).

## What Was Built
- Bullet list of features, endpoints, components, etc.

## Technical Changes
- Schema changes (SQL change scripts added)
- New API endpoints or application handlers
- New Blazor or React components
- Configuration changes

## Decisions Made
- Any architectural or UX decisions that came up during implementation.

## Test Coverage
- Summary of what's tested and any gaps.

## Next Steps
- What logically follows from this sprint.
- Any deferred items or known issues.

Guidelines

  • Write for a future developer (or future you) who needs to understand what happened.
  • Be specific. "Added trade tracking" is useless. "Added POST /api/v1/trades endpoint with EF-backed TradeRepository, FluentValidation, audit timestamps, and xUnit integration tests against Testcontainers SQL Server" is useful.
  • If the PRD had tasks that weren't completed, note them in Next Steps.
  • Keep it factual. This is a record, not a sales pitch.
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. yesterday First seen · 56 lines · 14 tokens per session scan A 478464bb44b8

Subscribe to this mod's changes

pm is an agent published in the GitHub repository robconery/chappie (11 stars, last pushed 4mo ago), licensed MIT. It adds 14 tokens to every session and 436 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 2026-08-30.