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/plankanpx skills add ssube/conclave --skill plankagit clone --depth 1 https://github.com/ssube/conclaveWhat 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 | $0.00048 | $0.01049 |
| Opus 5 | $0.00024 | $0.00524 |
| Sonnet 5 | $0.00010 | $0.00210 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
planka 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planka Skill
Manage tasks and projects using the Planka kanban board.
Actions
| Action | Description |
|---|---|
create |
Create a new card in a list |
list |
List cards, optionally filtered by list or label |
get |
Get details for a specific card (includes comments and tasks) |
move |
Move a card to a different list |
complete |
Move a card to the done list |
update |
Update card title, description, or labels |
comment |
Add a comment to a card |
delete |
Delete a card |
boards |
List available boards |
labels |
List available labels |
Usage
python3 {baseDir}/planka.py [--board <name>] <command> [options]
Create a new card
When creating cards, use the template in {baseDir}/references/card-template.md to
structure the card description. Fill in each section (Goal, Context, Requirements,
Considerations, Acceptance Criteria) based on the task at hand.
Add the human label for tasks created by or intended for a human, and the agent
label for tasks the agent should work on autonomously.
python3 {baseDir}/planka.py create \
--title "Review image prompts" \
--description "$(cat <<'CARD'
## Goal
Check prompt quality and consistency across generated images.
## Context
Recent image generations have shown inconsistent styling. Need a review pass.
## Requirements
1. **Audit**: Review last 20 generated prompts for style consistency
2. **Scope**: Focus on character prompts first
## Acceptance Criteria
- [ ] All prompts reviewed and scored
- [ ] Inconsistent prompts flagged for revision
CARD
)" \
--list "next up" \
--labels "agent"
List cards
# List all cards on the default board
python3 {baseDir}/planka.py list
# Filter by column
python3 {baseDir}/planka.py list --list "next up"
# Filter by label
python3 {baseDir}/planka.py list --label "priority"
# Different board
python3 {baseDir}/planka.py --board dev list
Get card details
python3 {baseDir}/planka.py get <card-id>
What ships with it
2 files 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.
- 2d ago First seen · 162 lines · 48 tokens per session scan A a0dfea227c96
planka is a skill published in the GitHub repository ssube/conclave (2 stars, last pushed 6mo ago), licensed MIT. It adds 48 tokens to every session and 1,049 once invoked, about $0.0002 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
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
search
Search your MemPalace — semantic search across all mined memories, projects, and conversations.
tool-prompt-optimization
Optimize the description prompts an AI agent reads to learn its built-in tools (the .md files under prompts/tools/). Two halves: (1) measure how much of a prompt is already inferable from the tool's JSON parameter schema + name, to prune redundancy with evidence; (2) house authoring rules for what belongs in a tool…
mempalace-recall
Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…
docker-extend
Use when: User wants to extend Docker with custom tools, personalize the Docker environment, or set up user-specific Docker customization. Triggers: 'extend docker', 'docker-extend', 'add tools to docker', 'customize docker', 'add my tools to the container', 'personalize docker setup', 'docker user setup', 'install…
runjam-defaults
Default constraints for every RunJam session. Defines output path conventions, dependency checking rules, fallback strategies, and file management discipline. This skill is auto-injected into every session — do not remove. Current session working directory: /Users/guizhan/work/code/runjam.