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/phuonghx/aim-cli/aim-taskgit clone --depth 1 https://github.com/phuonghx/aim-cliWrote 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/phuonghx/aim-cli/aim-task)<a href="https://agentmods.dev/commands/phuonghx/aim-cli/aim-task"><img src="https://agentmods.dev/badge/commands/phuonghx/aim-cli/aim-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 | $0.00016 | $0.00410 |
| Opus 5 | $0.00008 | $0.00205 |
| Sonnet 5 | $0.00003 | $0.00082 |
| Haiku 4.5 | $0.00002 | $0.00041 |
Grade A, and why
aim-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 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
Task Management & Tracker
List, view, create, edit, or check off tasks under the .ai-context/tasks/ directory to manage and observe project progress.
Instructions:
- If listing tasks is requested, run
aim task listto check all tasks, assignees, and statuses. - If finding the next actionable task is requested, run
aim task nextto see the next task based on priority and dependencies. - If viewing a task is requested, run
aim task view <id>to display its parameters, description, and acceptance criteria. - If creating a task is requested, run the
aim task createcommand:aim task create "<title>" -d "<description>" --ac "<criteria1>" --ac "<criteria2>" -p [low|medium|high|urgent] -a [assignee] --parent [parent_id] --depends-on [dep_id]- Make sure acceptance criteria follow EARS syntax (WHEN/THEN, WHILE, etc.).
- If editing a task's status, assignee, or check/uncheck AC is requested, run the
aim task editcommand:aim task edit <id> -s [todo|in-progress|in-review|blocked|done]aim task edit <id> -a [assignee]- Mark AC index as completed (1-based):
aim task edit <id> --check-ac <index> - Add/remove dependency:
aim task edit <id> --add-dep <dep_id>or--remove-dep <dep_id> - Link spec/plan:
aim task edit <id> --spec [path]or--plan [path]
- Ensure task progress is updated in the conversation's
task.mdchecklist in the brain folder.
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 · 23 lines · 16 tokens per session scan A 139f8fbbf510
aim-task is a command published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 410 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 2026-09-03.
Other commands, from other repositories
critique-ux
Run a focused UX critique on a screen — affordances, information density, and hierarchy — and output a prioritised fix list.
design-onboarding
Design a first-run experience end to end — activation path, progressive disclosure, and time to first value.
frame-problem
Structure an ambiguous design challenge into a clear problem definition with constraints and criteria.
strategize
Develop a complete UX strategy for a product or feature area.
release
Prepare a release by updating docs and bumping the version.
eg-fix-bug
Fix a bug using the elephant/goldfish workflow — problem doc, goldfish diagnosis check, failing test, fix, review, validate.