find-tasks

find-tasks is a skill for Claude Code, Codex from OdinMB/ops-workflow. It costs 38 tokens per session (1,387 once invoked), scanned A, original, MIT.

A procedure for reviewing an operations repository's goals, current state, and backlog to identify work that is not yet tracked.

In plain words
What is it for?
Use it when deciding what the project should tackle next; it adds suitable work items to the backlog.
Why use it?
It reveals missing, stalled, or outdated work without starting that work automatically.

Skill for Claude CodeCodex

Part of the ops plugin — 9 skills, 10 commands, 5 agents shipped together

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.

agentmods
npx agentmods add skills/odinmb/ops-workflow/find-tasks
Any agent
npx skills add OdinMB/ops-workflow --skill find-tasks
Clone the repo
git clone --depth 1 https://github.com/OdinMB/ops-workflow

Made for: Claude Code, Codex.

Or install ops, the plugin that ships this one along with the rest of its 9 skills, 10 commands, 5 agents.

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 find-tasks

README.md
[![agentmods](https://agentmods.dev/badge/skills/odinmb/ops-workflow/find-tasks.svg)](https://agentmods.dev/skills/odinmb/ops-workflow/find-tasks)
Your own site
<a href="https://agentmods.dev/skills/odinmb/ops-workflow/find-tasks"><img src="https://agentmods.dev/badge/skills/odinmb/ops-workflow/find-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,387 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00038 $0.01387
Opus 5 $0.00019 $0.00694
Sonnet 5 $0.00008 $0.00277
Haiku 4.5 $0.00004 $0.00139

Measured 3d ago against content hash bfda9076c643, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

find-tasks 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.

skills/find-tasks/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ops Find Tasks

Analyze the project's goals, current state, and existing backlog to surface new work items that would move the project forward. The output is new backlog entries — this skill does NOT execute them.

Context Required

Before running this skill, you need the project overview already loaded (MEMORY.md, state files, backlog, recent plans). If you don't have it, gather it now following the same context-loading steps as ops:whats-next.

Analysis Lenses

Examine the project through these lenses to find work that isn't already tracked. Skip lenses that don't apply to the project.

1. Goal Gaps

Compare the project's stated goals (from MEMORY.md and state files) against what's actually being tracked in the backlog:

  • Goals with no corresponding backlog items or active plans
  • Goals where progress has stalled — the last related completed plan is old
  • Sub-goals or prerequisites that are implied but not explicitly tracked

2. Stale State

State files describe reality. When reality changes, state files need updating:

  • State entries older than 60 days that likely need refreshing (market data, competitor info, pricing, statistics)
  • State entries that reference external resources that may have changed
  • Missing state files for aspects of the project that have evolved since the last update

3. Research Opportunities

Knowledge gaps that could be filled with web research or analysis:

  • Competitors, tools, or platforms mentioned in goals but not yet researched
  • Industry trends relevant to the project's domain
  • Best practices or case studies that could inform strategy
  • Reference material that would strengthen existing plans

4. Content & Artifact Gaps

Deliverables that would be useful based on the project's current trajectory:

  • Templates, frameworks, or checklists referenced in plans but not yet created
  • Drafts that are needed as prerequisites for backlog items
  • Documentation that would make future work easier

5. Follow-Through

Read the full file on GitHub · 120 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. 3d ago First seen · 120 lines · 38 tokens per session scan A bfda9076c643

Subscribe to this mod's changes

find-tasks is a skill published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 16d ago), licensed MIT. It adds 38 tokens to every session and 1,387 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.