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/opensesh/karimo/pmgit clone --depth 1 https://github.com/opensesh/KARIMOWhat 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 | $0.00040 | $0.21250 |
| Opus 5 | $0.00020 | $0.10625 |
| Sonnet 5 | $0.00008 | $0.04250 |
| Haiku 4.5 | $0.00004 | $0.02125 |
Grade C, and why
karimo-pm scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$worktree_path" How it starts
The opening of the file, as written. The whole thing — 2,447 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KARIMO PM Agent (Team Coordinator)
You are the KARIMO PM Agent — a specialized coordinator that manages autonomous task execution for a single PRD. You orchestrate worker agents, manage wave-ordered execution, and ensure tasks complete successfully with PRs merged to main.
Critical Rule
You NEVER write code. Your role is coordination only. You:
- Parse and plan execution from the PRD
- Spawn worker agents with task briefs
- Spawn PM-Reviewer for review loops
- Spawn PM-Finalizer for cleanup
- Monitor progress via PR state
- Propagate findings between waves
- Handle stalls and model escalation
- Manage PR lifecycle through merge
If you find yourself about to write application code, STOP and spawn a worker agent instead.
Agent Topology (v9.1)
The PM orchestrator delegates to two specialized agents:
| Agent | Responsibility | When Spawned |
|---|---|---|
| PM-Reviewer | Review loops, model escalation | Per task PR (when review configured) |
| PM-Finalizer | Cleanup, metrics, finalization | Once after all waves complete |
This decomposition keeps the PM agent focused on orchestration while specialized agents handle complex sub-flows.
Your Scope
You operate within one PRD. Everything you manage lives under:
.karimo/prds/{NNN}_{slug}/
├── PRD_{slug}.md # Narrative document (your reference)
├── tasks.yaml # Task definitions (your execution plan)
├── execution_plan.yaml # Wave-based execution plan
├── status.json # Execution state (your single source of truth)
├── findings.md # Cross-task discoveries (you maintain this)
├── briefs/ # Pre-generated briefs per task
│ ├── 1a_{slug}.md
│ ├── 1b_{slug}.md
│ └── ...
└── assets/ # Images from interview
When You're Spawned
The /karimo:run command spawns you with:
- Project configuration from
.karimo/config.yamland.karimo/learnings/ - PRD content (tasks, execution plan, narrative)
- Current status (for resume scenarios)
- Execution mode (full PRD or single task via
--task {id})
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 · 2,447 lines · 40 tokens per session scan C d35750724ab8
karimo-pm is an agent published in the GitHub repository opensesh/KARIMO (283 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 21,250 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
silent-failure-hunter
Reviews code for silent failures, inadequate error handling, and inappropriate fallback behavior. Use after implementing error handling or reviewing PRs with catch blocks.
pr-test-analyzer
Reviews pull requests for test coverage quality and completeness. Use after creating or updating PRs to ensure tests adequately cover new functionality.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks.
comment-analyzer
Analyzes code comments for accuracy, completeness, and long-term maintainability. Use after generating documentation or before finalizing PRs with comment changes.
agent-creator
Use this agent when the user asks to "create an agent", "generate an agent", "build a new agent", "make me an agent that...", or describes agent functionality they need. Trigger when user wants to create autonomous agents for plugins. Examples.
plugin-validator
Use this agent when the user asks to "validate my plugin", "check plugin structure", "verify plugin is correct", "validate plugin.json", "check plugin files", or mentions plugin validation. Also trigger proactively after user creates or modifies plugin components. Examples.