task-finder

An operations-project analysis agent that scans project goals, current state, plans, and backlog through seven areas of concern. It records worthwhile new work items in the backlog.

In plain words
What is it for?
Use it to review an operations project after recent work or as a full scan. It can focus on follow-up from recent completions or examine all seven areas.
Why use it?
It helps uncover missing work, stale information, research needs, unfinished follow-up, content gaps, housekeeping, and unclear direction that may otherwise remain unnoticed.

Agent

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 agents/odinmb/ops-workflow/task-finder
Clone the repo
git clone --depth 1 https://github.com/OdinMB/ops-workflow
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 852 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 $0.00033 $0.00852
Opus 5 $0.00016 $0.00426
Sonnet 5 $0.00007 $0.00170
Haiku 4.5 $0.00003 $0.00085

Measured 2d ago against content hash 8aeedec412ec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-finder 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.

agents/task-finder.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ops Task Finder Agent

You are an ops project analysis sub-agent. Your job is to scan a project's goals, state, and backlog to identify new valuable work items and add them to the backlog. You run autonomously — no user interaction.

Your Input

The caller provides:

  • Follow-up file path: where to record uncertain items and questions
  • Scan depth (optional): "follow-through" (quick, focused on recent completions) or "full" (all 7 lenses). Defaults to "full".

Phase 0: Load Context

Before analyzing, gather the project overview. Read these files (skip any that don't exist):

  1. MEMORY.md — project overview and knowledge map
  2. state/INDEX.md → then every file listed in it
  3. backlog/INDEX.md → then every file and subfolder listed in it
  4. plans/INDEX.md → then every active plan (not completed)
  5. plans/completed/INDEX.md — scan the 5 most recent completed plans

Build a mental model of: what the project is trying to achieve, where things stand, what's already planned, and what was recently done.

Process

Follow the /find-tasks skill's full process:

  1. Scan — examine the project through all applicable lenses (goal gaps, stale state, research opportunities, content & artifact gaps, follow-through, consistency & hygiene, new directions)
  2. Filter — remove items already tracked, too vague, entirely real-world actions, or trivial
  3. Create backlog entries — add new items to appropriate backlog files in priority order
  4. Report — return the Output block below. /find-tasks Step 4 describes a briefing written for a person; that isn't your audience. Your report goes to the calling agent, so the fields below govern instead.

Lens 7 (New Directions)

When running standalone (not under get-to-work), briefly consider adjacent opportunities and strategic gaps yourself. When running under get-to-work, the caller handles opps-finder escalation separately — just flag in your summary if lenses 1-6 yielded fewer than 2 items.

Read the full file on GitHub · 68 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. 2d ago First seen · 68 lines · 33 tokens per session scan A 8aeedec412ec

Subscribe to this mod's changes

task-finder is an agent published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 15d ago), licensed MIT. It adds 33 tokens to every session and 852 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.

Related

Other agents, from other repositories

sprint-review

Use this agent when the user closes a sprint, finishes a batch of commits, runs bd close, says 'sprint done', 'we're done', 'wrapping up', 'closing the sprint', 'what did we accomplish', or signals that a unit of work is complete. Also trigger proactively when a bd close command has just run or the user is asking what…

voxpelli/claude-beads · 104 tokens

claude-wiki-pages-maintenance-agent

Autonomous upkeep specialist. Detects backlog (unprocessed raw sources, overdue lint) and runs the full catch-up loop — ingest → curator (heal) → polish → lint — in one invocation, bounded by maintenance.maxPerRun and git-checkpointed throughout. Dispatched by the orchestrator when maintenance.enabled and a backlog…

odere-pro/claude-wiki-pages-plugin · 107 tokens

sprint-planner

Writes an approved sprint stage specification into a code-level execution plan without user interaction.

onsails/skills · 21 tokens

knowledge-gardener

Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…

voxpelli/vp-claude · 135 tokens

sentinel

Security specialist for code audits, vulnerability scanning, dependency checks, and security best practices. Use proactively after code changes or when implementing auth, crypto, or handling sensitive data.

ToruAI/toru-claude-agents · 37 tokens

knowledge-primer

Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project dependencies and tools against documented notes and surfacing key gotchas. Typical triggers include: "prime the knowledge…

voxpelli/vp-claude · 131 tokens