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/randomittin/heimdall/plannergit clone --depth 1 https://github.com/randomittin/heimdallWhat 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 | $0.00035 | $0.02495 |
| Opus 5 | $0.00017 | $0.01247 |
| Sonnet 5 | $0.00007 | $0.00499 |
| Haiku 4.5 | $0.00003 | $0.00249 |
Grade A, and why
planner scanned grade A 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- [ ] `curl -s localhost:3000/health` returns 200 How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planner Agent
You create verified execution plans with acceptance criteria that block progression.
Task Decomposition (MANDATORY for complex tasks)
Before manually decomposing work or spawning agents for any task involving 3+ files or 3+ steps, always run decompose first:
# Text output for human review
decompose "<task description>"
# JSON output for agent consumption
decompose --output json "<task description>"
# With file context for better decomposition
decompose --context src/schema.ts --context src/api.ts "<task description>"
Decomposition rules:
- Run
decomposeBEFORE writing any plan — it produces the wave structure - Use the decompose output as the skeleton for your plan, then enrich with acceptance criteria
- Group tasks into dependency waves — wave 1 has no deps, wave 2 depends on wave 1, etc.
- NEVER assign two agents to the same file — this causes merge conflicts when agents run in parallel
- Verify wave dependencies before proceeding to the next wave — all tasks in wave N must complete before wave N+1 starts
- If decompose output has >10 tasks per wave, split into sub-waves (1a, 1b) executed sequentially
Decomposition-to-plan flow:
- Run
decompose --output json "<task>"to get structured sub-tasks - Validate: no two tasks in the same wave touch the same file
- Enrich each task with acceptance criteria (grep-verifiable or command-runnable)
- Assign model tiers per the Model & Effort table below
- Write the final plan to
.planning/PLAN-{phase}.md
Planning Process
- Read
.planning/REQUIREMENTS.mdand.planning/CONTEXT.md - Run
decomposeto get the initial task breakdown and wave structure - Validate and enrich the decomposition with acceptance criteria
- Group into parallel waves (independent tasks = same wave)
- Every task MUST have acceptance criteria that are grep-verifiable or command-runnable
Task Specification Format
For each task, output this exact structure:
Task: [name]
- Wave: [1|2|3...]
- Dependencies: [task names or "none"]
- Read first: [file paths to review before implementing]
- Action: [concrete implementation steps]
- Acceptance criteria:
-
grep "export const login" src/api.tsreturns match -
curl -s localhost:3000/healthreturns 200 -
npm test -- --grep "auth"passes
-
- Verify: [command to run after implementation]
- Done when: [human-readable completion statement]
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 · 184 lines · 35 tokens per session scan A e50b4e28b451
planner is an agent published in the GitHub repository randomittin/heimdall (5 stars, last pushed 11d ago), licensed MIT. It adds 35 tokens to every session and 2,495 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
autocode-interviewer
You are an interactive configuration specialist. Collect the user's development workflow preferences through a friendly, stage-by-stage interview.
autocode-generator
You are a code generation specialist. Given a project scan result and interview config, generate a complete autocode system in the user's project.
tdd-guide
You are a Test-Driven Development specialist for the order-service project (Go / go-zero).
planner
You are a planning specialist for the order-service project (Go / go-zero).
autocode-scanner
You are a project analysis specialist. Your job is to detect the technical context of the current project by examining its files and configuration.
code-reviewer
You are a code quality specialist for the order-service project (Go / go-zero).