pm-tasks-asana

pm-tasks-asana is a skill for Codex from llodev/skills. It costs 222 tokens per session (4,377 once invoked), scanned B, original, MIT.

An Asana adapter for turning plans or instructions into Asana tasks and managing existing tasks. Asana is a work-management service for organising tasks and projects.

In plain words
What is it for?
Use it to format or publish tasks, add comments, check subtasks, close tasks, assign people, change due dates, and execute plan files against existing Asana work.
Why use it?
It removes the need to manually translate a plan into Asana’s format or handle routine task updates separately.

Skill for Codex

Written for Codex: reads ~/.codex or $CODEX_HOME. Also seen: mentions Claude Code; mentions Codex; built for cline.

Good fit Use it to format or publish tasks, add comments, check subtasks, close tasks, assign people, change due dates, and execute plan files against existing Asana work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/llodev/skills/pm-tasks-asana
Install

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.

Any agent
npx skills add llodev/skills --skill pm-tasks-asana
Clone the repo
git clone --depth 1 https://github.com/llodev/skills

Made for: Codex.

Wrote 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.

agentmods badge for pm-tasks-asana

README.md
[![agentmods](https://agentmods.dev/badge/skills/llodev/skills/pm-tasks-asana/github.svg)](https://agentmods.dev/skills/llodev/skills/pm-tasks-asana)
Your own site
<a href="https://agentmods.dev/skills/llodev/skills/pm-tasks-asana"><img src="https://agentmods.dev/badge/skills/llodev/skills/pm-tasks-asana/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.

agentmods 80×15 button for pm-tasks-asana

Your own site · 80×15
<a href="https://agentmods.dev/skills/llodev/skills/pm-tasks-asana"><img src="https://agentmods.dev/badge/skills/llodev/skills/pm-tasks-asana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 222 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00222 $0.04377
Opus 5 $0.00111 $0.02188
Sonnet 5 $0.00044 $0.00875
Haiku 4.5 $0.00022 $0.00438

Measured 9d ago against content hash 6f914ec05bf2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

pm-tasks-asana scanned grade B with 1 finding 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 9d ago.

The scan reads SKILL.md. This mod also ships 9 executable files (src/adapter.ts, src/bin/init.ts, src/doctor-cli.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

- **Codex**: TOML entry under `[mcp_servers.asana]` in `~/.codex/config.toml`.
skills/pm-tasks-asana/SKILL.md · 203 lines

How it starts

The opening of the file, as written. The whole thing — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.

pm-tasks-asana

Adapter for Asana within the @llodev/pm-tasks-* family. Use the core skill's extraction phases, then apply Asana formatting and optionally publish/operate via the claude.ai Asana MCP server.

Routing

Mode Trigger Path
Paste-only "format as Asana task" without MCP intent Phase 3 (core) → Phase 4 (this skill, format only) → output paste blocks
MCP publish "publish to Asana", "create on Asana", "--publish-asana" Phase 3 → Phase 4 → Phase 5 (publish via MCP)
Autonomous [autonomous] or --auto in prompt OR LLODEV_PM_TASKS_AUTONOMOUS=1 Phase 3 → Phase 4 → Phase 5b (write-through, no preview)
CRUD ops "check subtask N on task X", "close task Y", "assign Alice to task Z", "comment on task X" Phase 6 (operations, direct verb dispatch)
Plan-execution Plan file path in prompt (docs/plans/*.md), OR --plan-exec flag, OR plan reference paired with .asana.json Phase 7 (discover existing cards via discoverPlanTasks; calling agent dispatches per-task verbs at task boundaries)

Read the full file on GitHub · 203 lines

Changes

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.

  1. 9d ago First seen · 203 lines · 222 tokens per session scan B 6f914ec05bf2

Subscribe to this mod's changes

pm-tasks-asana is a skill published in the GitHub repository llodev/skills (2 stars, last pushed yesterday), licensed MIT. It adds 222 tokens to every session and 4,377 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.