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.
git clone --depth 1 https://github.com/MohammadShehadeh/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mohammadshehadeh/agent-skills/plan-task)<a href="https://agentmods.dev/commands/mohammadshehadeh/agent-skills/plan-task"><img src="https://agentmods.dev/badge/commands/mohammadshehadeh/agent-skills/plan-task.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00027 | $0.00338 |
| Opus 5 | $0.00014 | $0.00169 |
| Sonnet 5 | $0.00005 | $0.00068 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
plan-task 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 7d 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.
What it actually says
Plan the following task before writing any code: $ARGUMENTS
- Restate the task as verifiable targets. Turn vague asks into concrete, checkable outcomes ("add validation" → "these inputs are rejected with these error keys, covered by tests").
- State assumptions out loud. If the request is ambiguous, ask — do not pick an interpretation and run. Say "I don't know" instead of guessing.
- List the surgical change set. Exactly which files change and why each traces back to the request. Include an explicit out-of-scope list — files/behaviors that look related but must not be touched.
- Propose the simplest approach that solves the problem — no speculative abstractions. If a simpler approach than the one implied exists, push back and say so.
- Define machine-checkable done criteria. Commands and expected results using the repo's scripts (e.g.
npm run typecheck/pnpm typecheckexits 0, test command passes including N new tests,grepfor the old pattern returns nothing) — never prose like "works correctly". - Name the STOP conditions. The key assumptions the plan rests on; if any turns out false during implementation, stop and report instead of improvising.
- Stop and wait for confirmation. Do not write code until the approach is approved.
Be concise throughout.
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.
- 7d ago First seen · 17 lines · 27 tokens per session scan A 0a46212de5e9
plan-task is a command published in the GitHub repository MohammadShehadeh/agent-skills (2 stars, last pushed 23d ago), licensed MIT. It adds 27 tokens to every session and 338 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 2026-08-31.
Other commands, from other repositories
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.
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.