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 skills/ssube/conclave/project-planningnpx skills add ssube/conclave --skill project-planninggit clone --depth 1 https://github.com/ssube/conclaveWrote 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/ssube/conclave/project-planning)<a href="https://agentmods.dev/skills/ssube/conclave/project-planning"><img src="https://agentmods.dev/badge/skills/ssube/conclave/project-planning.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 | $0.00050 | $0.00791 |
| Opus 5 | $0.00025 | $0.00396 |
| Sonnet 5 | $0.00010 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
project-planning 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 3d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Planning Skill
Transform a concept into an actionable specification through structured interview-style questioning. The output is a Markdown plan document and optionally a set of Planka cards ready for the board.
When to Use
- A concept needs to become actionable work
- A new project or content initiative needs scoping before execution
- Before starting a multi-phase effort
Process
The Interview
The interview has seven phases. Not every phase applies to every project — skip what doesn't serve the work.
Phase 1: Vision
- What is the project in one sentence?
- What prompted this?
- What does success look like? Be specific.
Phase 2: Scope
- What concrete things will this project produce?
- What will it explicitly NOT do?
- What already exists that we can build on?
- What is the minimum viable version?
Phase 3: Audience
- Who is the primary audience?
- What do they want from this?
- Where will they encounter it?
- What action do we want them to take?
Phase 4: Deliverables
For each deliverable: what, format/specs, who creates it, where it lives, dependencies, approval needed?
Phase 5: Dependencies & Blockers
- What skills/tools are required?
- What human actions are required?
- What information is missing?
- What are the risks?
Phase 6: Execution Plan
- Break work into phases — each phase produces something tangible
- Identify what can be parallelized
- Estimate effort for each phase
- Define checkpoints
- Identify the first concrete action
Phase 7: Cards
- Which Planka board and list?
- For each card: title, description, labels, dependencies
Quick Mode
For small tasks that need tracking but not full planning:
python3 {baseDir}/plan.py new "fix-session-bug" --quick
Quick mode creates a lightweight plan with just: What, Why, Done-looks-like, First action.
Usage
Start a new plan
python3 {baseDir}/plan.py new "website-content-update"
Creates a template at the configured plans directory.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 3d ago First seen · 129 lines · 50 tokens per session scan A 6e6a90856b82
project-planning is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 791 once invoked, about $0.0003 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 skills, from other repositories
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
ralph-two-pass-scan
Confidence: high Domain: work-monitoring Last validated: 2026-03-24.
jira
Read and write Jira issues, comments, transitions via the Jira REST API v3.
todoist
Manage Todoist tasks and projects via the Todoist REST API v2.
trello
Manage Trello boards, lists, and cards via the Trello REST API.
file-todos
Manage file-based todo tracking in the todos/ directory.