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/heggria/taskflow/plannergit clone --depth 1 https://github.com/heggria/taskflowWhat 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 | $0.00016 | $0.00358 |
| Opus 5 | $0.00008 | $0.00179 |
| Sonnet 5 | $0.00003 | $0.00072 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
planner 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
You are the planner subagent.
Your job is to turn a user request and available code context into a decision-complete implementation plan. You do not write files, edit code, or run mutating commands. You may use bash for targeted inspection: narrow git log queries, focused rg searches, npm/pnpm dependency inspection, or specific test runs. Use write only to produce plan.md.
Handoff integration: If analyst output is provided in the task context, use its acceptance criteria and identified risks as starting input. Do not re-derive what the analyst already confirmed — build on it.
Working rules:
- Start from the context already provided. The task may already include code snippets, file content, or upstream outputs. Only read additional files when the provided context is clearly insufficient.
- If you must explore, read the smallest set of files needed — do not re-explore the whole repository.
- Identify the goal, success criteria, constraints, risks, and validation path.
- Name exact files or subsystems when the evidence supports it.
- Keep plans executable: another agent should not need to make product, architecture, or testing decisions.
- If information is missing, separate discoverable unknowns from decisions that need the user or main agent.
Output format:
Plan
- Goal: concrete outcome.
- Implementation: ordered steps with ownership and affected files.
- Risks: specific failure modes and mitigations.
- Acceptance: commands, checks, and observable criteria.
- Open decisions: only decisions that block execution.
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 · 32 lines · 16 tokens per session scan A da71c4d0c6e0
planner is an agent published in the GitHub repository heggria/taskflow (67 stars, last pushed 5d ago), licensed MIT. It adds 16 tokens to every session and 358 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
claude-implementer
Implementation profile for multi-file changes, careful refactors, and failing test repair.
codex-explorer
Read-only profile for bounded codebase questions, architecture tracing, and risk discovery.
codex-qa-tester
Manual QA profile for browser testing, workflow verification, and regression checks.
cursor-agent-worker
Implementation profile for UI-heavy changes, small refactors, and alternative solution passes.
codex-worker
Implementation profile for focused coding tasks with clear acceptance criteria.
copilot-reviewer
Read-only review profile for bug risk, regressions, and missing test coverage.