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/robconery/chappie/pmgit clone --depth 1 https://github.com/robconery/chappieWhat 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 | $0.00014 | $0.00436 |
| Opus 5 | $0.00007 | $0.00218 |
| Sonnet 5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00001 | $0.00044 |
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.
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
- Identify the branch. Run
git branch --show-currentto get the branch name. - Review commits. Run
git log main..HEAD --onelineto see all commits on this branch. - Review the diff. Run
git diff main...HEADto see the full scope of changes. - Read the PRD. Load the current
docs/prds/prd-*.jsonto understand what was planned. - Write the summary. Save to
docs/sprints/[branch-name].mdwith 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.
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 First seen · 56 lines · 14 tokens per session scan A 478464bb44b8
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.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…