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/el-feo/ai-context/create-tasksgit clone --depth 1 https://github.com/el-feo/ai-contextWhat 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 | $0.00022 | $0.03809 |
| Opus 5 | $0.00011 | $0.01904 |
| Sonnet 5 | $0.00004 | $0.00762 |
| Haiku 4.5 | $0.00002 | $0.00381 |
Grade A, and why
create-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 2d ago.
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 — 458 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolution order if omitted:
- Most recent open Epic issue:
gh issue list -l Epic -s open --limit 1 --json number -q '.[0].number'
<usage_examples> With epic number:
/ghpm:create-tasks epic=#42
With PRD number (creates tasks for all linked Epics):
/ghpm:create-tasks prd=#10
Auto-resolve most recent Epic:
/ghpm:create-tasks
</usage_examples>
<operating_rules>
- Do not ask clarifying questions. Make assumptions and record them.
- Do not create local markdown files. All output goes into GitHub issues/comments.
- Tasks must be atomic and independently executable by a human or agent.
- Each Task must include all context needed for its scope (plus links to Epic/PRD).
- Each Task MUST include a Commit Type (
feat,fix,refactor, etc.) and Scope for conventional commits. - Task count must be proportional to Epic scope - see guidance below.
- Each Task MUST have a Fibonacci estimate (1, 2, 3, 5, or 8) - see estimation guidance below. </operating_rules>
<estimation_guidance>
Fibonacci Estimation Scale
Assign a Fibonacci estimate to each Task based on relative complexity. Estimates reflect effort/complexity, not hours.
| Estimate | Complexity | Examples |
|---|---|---|
| 1 | Trivial | Update README, fix typo, change config value |
| 2 | Simple | Add a single test, update documentation section, simple refactor |
| 3 | Moderate | Add simple feature, refactor small module, add validation |
| 5 | Complex | Multi-file feature, significant refactor, new API endpoint |
| 8 | Very Complex | Cross-cutting feature, complex integration, architectural change |
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.
- 2d ago First seen · 458 lines · 22 tokens per session scan A 4292609b7ead
create-tasks is a command published in the GitHub repository el-feo/ai-context (12 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 3,809 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.