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/walterra/eddoapp/eddo-todonpx skills add walterra/eddoapp --skill eddo-todogit clone --depth 1 https://github.com/walterra/eddoappWrote 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/walterra/eddoapp/eddo-todo)<a href="https://agentmods.dev/skills/walterra/eddoapp/eddo-todo"><img src="https://agentmods.dev/badge/skills/walterra/eddoapp/eddo-todo.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 | $0.00072 | $0.02883 |
| Opus 5 | $0.00036 | $0.01442 |
| Sonnet 5 | $0.00014 | $0.00577 |
| Haiku 4.5 | $0.00007 | $0.00288 |
Grade A, and why
eddo-todo scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eddo Todo
Task management for the coding agent. Track todos, manage projects, log time.
Step 1: Set EDDO path (the CLI lives in this skill's directory):
# Inside Docker container:
EDDO="/home/agent/.pi/agent/skills/eddo-todo/eddo-todo.js"
# Or use environment variable if set:
EDDO="${PI_CODING_AGENT_DIR:-/home/agent/.pi/agent}/skills/eddo-todo/eddo-todo.js"
Step 2: Build METADATA (extract values from <pi_session_metadata> in your context):
BRANCH=$(git branch --show-current 2>/dev/null || echo "none")
METADATA='{"agent:session":"YOUR_PI_SESSION_ID","agent:model":"YOUR_PI_MODEL","agent:cwd":"YOUR_PI_CWD","agent:branch":"'$BRANCH'"}'
Replace YOUR_PI_SESSION_ID, YOUR_PI_MODEL, YOUR_PI_CWD with actual values from <pi_session_metadata>.
Step 3: Use the variables:
$EDDO next
$EDDO get <id>
$EDDO create "Task" -c context -t gtd:next -M "$METADATA" -D "task description" -m "why creating this"
⚠️ DO NOT look for eddo.js in the current working directory - it's in the skill directory.
⚠️ DO NOT use placeholder text like <PI_SESSION_ID> literally - substitute actual values.
Related Skills
- eddo-work: Structured phases for implementing complex tasks (REFINE → IMPLEMENT → REVIEW → COMPLETE → GITHUB_PR)
Setup
Prerequisite: Eddo MCP server accessible from container (via Docker network)
# Inside Docker container:
EDDO="/home/agent/.pi/agent/skills/eddo-todo/eddo-todo.js"
# The MCP URL should be set via environment variable by the container orchestrator
# Default: http://host.docker.internal:3001/mcp (to reach host's MCP server)
export EDDO_MCP_URL=${EDDO_MCP_URL:-http://host.docker.internal:3001/mcp}
# MCP API key (stored in user preferences)
export EDDO_MCP_API_KEY=${EDDO_MCP_API_KEY:-""}
Short Flags
ALWAYS use short flags - saves tokens:
| Short | Long | Short | Long |
|---|---|---|---|
-c |
--context |
-t |
--tag |
-d |
--due |
-m |
--message |
-D |
--description |
-l |
--link |
-e |
--external-id |
-E |
--clear-external-id |
-p |
--parent-id |
-P |
--clear-parent |
-b |
--blocked-by |
-B |
--clear-blockers |
-M |
--metadata |
-u |
--undo |
What ships with it
4 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.
- 5d ago First seen · 298 lines · 72 tokens per session scan A e2aea0fda64f
eddo-todo is a skill published in the GitHub repository walterra/eddoapp (58 stars, last pushed 3d ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,883 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
artifact-management
Use for PACEflow artifact fields and formats: task indexes, CHG/HOTFIX lifecycle operations, artifact-writer prompts, approvals, verification, and archive.
pace-bridge
Use to bridge a confirmed Superpowers/native plan into PACEflow CHG/HOTFIX artifacts, create artifact-writer prompts, and mark the specific plan as synced.
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
repo-recap
Generate a comprehensive repo recap (PRs, issues, releases) for sharing with team. Pass "en" or "fr" as argument for language (default fr).
team
N coordinated agents on shared task list using Claude Code implicit agent teams.
omc-plan
Strategic planning with optional interview workflow.