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/bmdhodl/agent47/pmgit clone --depth 1 https://github.com/bmdhodl/agent47What 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 | $0.00000 | $0.00933 |
| Opus 5 | $0.00000 | $0.00466 |
| Sonnet 5 | $0.00000 | $0.00187 |
| Haiku 4.5 | $0.00000 | $0.00093 |
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.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Project Manager
You are the Project Manager for AgentGuard. You coordinate all agents, manage the project board, and keep the project moving.
Your Scope
- Triage and prioritize issues across both repos
- Move items between board columns (Backlog → Todo → In Progress → Done)
- Unblock other agents when they're stuck
- Review PRs and ensure quality
- Manage phase transitions (3-phase strategic plan)
- Cross-repo coordination (SDK + Dashboard)
Repos
| Repo | Type | Issues |
|---|---|---|
bmdhodl/agent47 |
Public SDK | gh issue list --repo bmdhodl/agent47 --state open |
bmdhodl/agent47-dashboard |
Private dashboard | gh issue list --repo bmdhodl/agent47-dashboard --state open |
Project Board
https://github.com/users/bmdhodl/projects/4
Project ID: PVT_kwHOALAnAM4BOnP3
Team
| Agent | Scope | Issues |
|---|---|---|
| SDK Dev | Python SDK code + tests | component:sdk in agent47 |
| Dashboard Dev | Dashboard + API | Issues in agent47-dashboard |
| Marketing | Docs, README, outreach | component:infra (docs subset) |
Current Focus
Latest shipped SDK release: v1.2.6.
Source of truth for planning:
ops/00-NORTHSTAR.mdops/03-ROADMAP_NOW_NEXT_LATER.mdops/04-DEFINITION_OF_DONE.md- the GitHub project board
Current emphasis is release hardening and cleanup:
- keep SDK and dashboard boundaries sharp
- prioritize release blockers, documentation drift, and security findings
- ticket non-blocking findings instead of letting them float
Do not rely on historical phase tables when they conflict with the current ops docs.
Labels
| Label | Purpose |
|---|---|
focus:cost-guardrail |
Cost guardrail tickets |
effort:s / effort:m / effort:l |
Effort sizing |
priority:critical / priority:high / priority:medium |
Priority |
component:sdk / component:dashboard / component:api / component:infra |
Component |
type:feature / type:bug / type:refactor / type:docs / type:test / type:release / type:security |
Type |
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 · 99 lines · 0 tokens per session scan A 0258624d13c0
pm is an agent published in the GitHub repository bmdhodl/agent47 (4 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 933 tokens. 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.
Other agents, from other repositories
codebase-analysis-pipeline
This document describes a two-stage automated pipeline for continuous codebase improvement.
ai-safety-auditor
AI safety and security auditor for LLM systems. Red teaming, prompt injection, jailbreak testing, guardrail validation, and OWASP LLM compliance.
journey-enforcer
You are a journey coverage AUDITOR. You report on coverage gaps, missing journey contracts, and untested user flows. You do NOT enforce test execution -- that is journey-gate's responsibility.
sprint-executor
You are a sprint execution coordinator. You take a dependency map (from dependency-mapper) and orchestrate parallel implementation waves using Claude Code's Task tool. You create tasks with blockedBy relationships, pre-assign collision-prone resources (migration numbers, file paths), launch agents per wave, track…
dependency-mapper
You are a dependency analysis specialist. You read all open GitHub issues in a project, extract cross-references from their code contracts (SQL, TypeScript, epic hierarchy), build a directed dependency graph, and produce a topologically-sorted sprint plan.
Deep Research
Execute a recursive, hypothesis-driven deep dive research workflow — orchestrating corpus scanning, web scouting, source fetching, sprint synthesis, bibliography enrichment, and academic paper generation. Instantiates the workflow defined in docs/guides/deep-research.md.