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 commands/fblgit/claudebench/tasksgit clone --depth 1 https://github.com/fblgit/claudebenchWhat 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 | $0.00536 |
| Opus 5 | $0.00000 | $0.00268 |
| Sonnet 5 | $0.00000 | $0.00107 |
| Haiku 4.5 | $0.00000 | $0.00054 |
Grade A, and why
tasks 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.
This is a copy
100% identical to tasks — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Break down the plan into executable tasks.
This is the third step in the Spec-Driven Development lifecycle.
Given the context provided as an argument, do this:
-
Run
scripts/check-task-prerequisites.sh --jsonfrom repo root and parse FEATURE_DIR and AVAILABLE_DOCS list. All paths must be absolute. -
Load and analyze available design documents:
- Always read plan.md for tech stack and libraries
- IF EXISTS: Read data-model.md for entities
- IF EXISTS: Read contracts/ for API endpoints
- IF EXISTS: Read research.md for technical decisions
- IF EXISTS: Read quickstart.md for test scenarios
Note: Not all projects have all documents. For example:
- CLI tools might not have contracts/
- Simple libraries might not need data-model.md
- Generate tasks based on what's available
-
Generate tasks following the template:
- Use
/templates/tasks-template.mdas the base - Replace example tasks with actual tasks based on:
- Setup tasks: Project init, dependencies, linting
- Test tasks [P]: One per contract, one per integration scenario
- Core tasks: One per entity, service, CLI command, endpoint
- Integration tasks: DB connections, middleware, logging
- Polish tasks [P]: Unit tests, performance, docs
- Use
-
Task generation rules:
- Each contract file → contract test task marked [P]
- Each entity in data-model → model creation task marked [P]
- Each endpoint → implementation task (not parallel if shared files)
- Each user story → integration test marked [P]
- Different files = can be parallel [P]
- Same file = sequential (no [P])
-
Order tasks by dependencies:
- Setup before everything
- Tests before implementation (TDD)
- Models before services
- Services before endpoints
- Core before integration
- Everything before polish
-
Include parallel execution examples:
- Group [P] tasks that can run together
- Show actual Task agent commands
-
Create FEATURE_DIR/tasks.md with:
- Correct feature name from implementation plan
- Numbered tasks (T001, T002, etc.)
- Clear file paths for each task
- Dependency notes
- Parallel execution guidance
Context for task generation: $ARGUMENTS
The tasks.md should be immediately executable - each task must be specific enough that an LLM can complete it without additional context.
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 · 60 lines · 0 tokens per session scan A eaf1b42cb33e
tasks is a command published in the GitHub repository fblgit/claudebench (9 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 536 tokens. A static security scan graded it A with 0 findings. It is 100% identical to tasks, differing in 4 lines, and is treated as a copy.
Other commands, from other repositories
pm-arch
Scan project structure and generate Mermaid architecture diagrams + flowcharts under .pm/architecture/.
pm-done
Close a todo (TODO-xxx), sync completed.md, refresh overview.
pm-review
Review local git diff with reasoning + snippets; cross-check; dispose findings into the rules library.
pm-status
Show governance health, wizard next step, all open blocking/high todos, and pending review count. Primary daily entry.
pm-charter
Create, import, discover, approve, or skip project charter. No-arg form is an interactive wizard.
pm-check
Diagnose .pm/ health (missing files, broken audit, stale map, unconfirmed PRD) and repair or increment without overwriting confirmed content.