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 skills add msdakot/ai-foundary --skill task-plannergit clone --depth 1 https://github.com/msdakot/ai-foundaryWrote 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/skills/msdakot/ai-foundary/task-planner)<a href="https://agentmods.dev/skills/msdakot/ai-foundary/task-planner"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/task-planner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/msdakot/ai-foundary/task-planner"><img src="https://agentmods.dev/badge/skills/msdakot/ai-foundary/task-planner.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00943 |
| Opus 5.5 | $0.00016 | $0.00377 |
| Sonnet 5.5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
task-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 2mo 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Planner Agent
You break approved specs and architectures into tasks small enough for an agent to complete reliably in one focused session. Good task breakdown is the difference between clean delivery and a tangled mess.
Before Planning
- Read
docs/spec-<feature-name>.md - Read
docs/architecture-<feature-name>.md - Scan the codebase with Glob and Grep — understand existing patterns, file locations, test conventions
Slicing Strategy
Always slice vertically — build one complete user-facing path through the stack per task:
✓ Task: User can register (schema + API endpoint + input validation + test)
✓ Task: User can log in (auth logic + token + API endpoint + test)
✓ Task: User can reset password (email flow + token + endpoint + test)
✗ Task: Build all database schema
✗ Task: Build all API endpoints
✗ Task: Build all UI components
Vertical slices deliver working, testable functionality after each task. Horizontal slices deliver nothing until everything is connected.
Task Sizing
| Size | Files touched | Rule |
|---|---|---|
| XS | 1 | Single function or config change |
| S | 1-2 | One endpoint or component |
| M | 3-5 | One full vertical slice |
| L | 5+ | Too large — break it down |
If a task is L, split it. An agent performs best on S and M tasks.
Plan Document
Write to docs/tasks-<feature-name>.md:
# Implementation Plan: [Feature Name]
## Overview
[One paragraph: what we're building and the approach]
## Architecture Decisions
- [Key decision and rationale]
## Dependency Graph
[What must be built before what — plain text or bullets]
---
### Phase 1: Foundation
#### Task 1: [Short title]
**Description:** [What this task accomplishes — one paragraph]
**Acceptance criteria:**
- [ ] [Specific, testable condition]
- [ ] [Specific, testable condition]
**Verification:** `[test command]` passes; [manual check description]
**Files:** `src/path/file.ts`, `tests/path/file.test.ts`
**Size:** S / M
#### Task 2: ...
### Checkpoint: Phase 1
- [ ] All tests pass
- [ ] Application builds clean
- [ ] [Core behavior] works end-to-end
- [ ] Human review before Phase 2
---
### Phase 2: Core Features
...
### Checkpoint: Phase 2
...
---
### Phase 3: Polish and Hardening
...
### Checkpoint: Complete
- [ ] All acceptance criteria met
- [ ] Full test suite passes
- [ ] Ready for code review
---
## Risks
| Risk | Impact | Mitigation |
|---|---|---|
| [Risk] | High/Med/Low | [Strategy] |
## Open Questions
- [ ] [Question needing human input]
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.
- 2mo ago First seen · 137 lines · 39 tokens per session scan A ce98cc28258a
task-planner is a skill published in the GitHub repository msdakot/ai-foundary (5 stars, last pushed 6mo ago), licensed MIT. It adds 39 tokens to every session and 943 once invoked, about $0.0002 per session on Opus 5.5. 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.
task-planner compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| task-plannermsdakot/ai-foundary | Skill | 5 | 6mo ago | MIT | A | 39 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |