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/odinmb/ops-workflow/find-tasksnpx skills add OdinMB/ops-workflow --skill find-tasksgit clone --depth 1 https://github.com/OdinMB/ops-workflowWrote 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/odinmb/ops-workflow/find-tasks)<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>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 | $0.00038 | $0.01387 |
| Opus 5 | $0.00019 | $0.00694 |
| Sonnet 5 | $0.00008 | $0.00277 |
| Haiku 4.5 | $0.00004 | $0.00139 |
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.
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
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 · 120 lines · 38 tokens per session scan A bfda9076c643
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.
Other skills, from other repositories
dev-finish
Close out a session — summarise what changed, capture what was learned, and prepare the commit.
dev-cycle
Run a feature end to end — scout the code, plan it, build it, and keep a session file so a closed terminal doesn't lose the thread.
raindrop-triage
This skill should be used when the user asks to 'triage unsorted bookmarks', 'clean up raindrop inbox', 'sort unsorted', 'organize bookmarks', 'raindrop triage', 'process bookmark backlog', 'promote triaged bookmarks', 'classify triaged', 'raindrop cleanup', 'deduplicate bookmarks', 'find duplicate bookmarks', 'tag…
factory-close
Close out a Linear issue — move to Done, add a closing comment, and clean up the local branch/worktree.
factory-setup-linear
Configure portable Linear workflow settings in .factory-kit/linear.json, migrating legacy .claude/linear.json settings when present.
factory-submit
Move the current branch's Linear issue to "In Review".