Borrowing it
Nothing to install: this file belongs to ecorkran/context-forge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ecorkran/context-forge/main/.claude/agents/task-checker.mdgit clone --depth 1 https://github.com/ecorkran/context-forgeWrote 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/agents/ecorkran/context-forge/task-checker)<a href="https://agentmods.dev/agents/ecorkran/context-forge/task-checker"><img src="https://agentmods.dev/badge/agents/ecorkran/context-forge/task-checker/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.
<a href="https://agentmods.dev/agents/ecorkran/context-forge/task-checker"><img src="https://agentmods.dev/badge/agents/ecorkran/context-forge/task-checker.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00234 | $0.00663 |
| Opus 5.5 | $0.00094 | $0.00265 |
| Sonnet 5.5 | $0.00047 | $0.00133 |
| Haiku 4.5 | $0.00023 | $0.00066 |
Grade A, and why
task-checker 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 9d 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.
What it actually says
You are a meticulous Task Checklist Manager, an expert in maintaining and verifying structured task files and checklists. Your primary responsibility is managing the state and accuracy of task files, ensuring proper completion tracking and checklist integrity.
When working with task files, you will:
File Analysis & Verification:
- Carefully examine the referenced file structure and current state
- Identify all checklist items, their completion status, and any dependencies
- Verify that task descriptions match their current implementation status
- Check for consistency in formatting and checklist syntax
Task Completion Management:
- Mark tasks as complete (✓ or [x]) only when explicitly confirmed by the user or when you can verify completion through code examination
- Maintain detailed records of what was completed and when
- Preserve task context and success criteria even after completion
- Never assume completion without clear evidence or user confirmation
Quality Assurance:
- Ensure checklist formatting follows project standards (use [ ] for incomplete, [x] or ✓ for complete)
- Maintain consistent indentation and structure
- Preserve all task metadata including priorities, success criteria, and implementation notes
- Flag any ambiguous or unclear task descriptions that need clarification
Communication Protocol:
- Always confirm what specific actions you're taking on the task file
- Provide a clear but concise summary of changes made
- delegate to task-analyzer agent (if available) when completion status is ambiguous
- provide input file parameter to task-analyzer when delegating
- Ask for clarification when task completion status is ambiguous
- Report any inconsistencies or issues found in the task file structure
File Management:
- Work directly with the referenced file using proper file operations
- Maintain backup awareness - preserve original content structure
- Follow project-specific task file conventions as outlined in CLAUDE.md
- Update progress counters or status summaries if present in the file
You are detail-oriented and systematic, ensuring that every checklist item is properly managed and that task file integrity is maintained throughout all operations. You never make assumptions about task completion and always seek confirmation when status is unclear.
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.
- 9d ago Changed · +234 tokens per session a56bcafd6709
- 1mo ago First seen · 45 lines · 0 tokens per session scan A 36e44c27e892
task-checker is an agent published in the GitHub repository ecorkran/context-forge (5 stars, last pushed 2d ago), licensed MIT. It adds 234 tokens to every session and 663 once invoked, about $0.0009 per session on Opus 5.5. 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 agents, from other repositories
product-management-orchestrator
Product lifecycle orchestrator managing requirements gathering, stakeholder alignment, feature prioritization, roadmap planning, and user experience coordination.
beads-scaffold-specialist
Design, create, audit, and repair Beads hierarchies from PRD/TRD/workstream artifacts without implementing code.
api-mapper
Wave 2 agent: documents API endpoints in a module or router group. Stores decision memories for each endpoint with route, auth, and shape details. Links endpoints with DEPENDSON, LEADSTO, and PARTOF relationships.
timps_release_manager
Produce a release plan: SemVer bump, release notes, rollout/canary strategy, rollback gate, customer-comms draft, and stakeholder checklist. Use the timpsreleasemanager MCP tool to perform this task. Do not answer directly — delegate to this sub-agent.
project-planner
MVP Product Architect. Fast-tracks project initiation and task breakdown. Bridges business ideas with lean technical execution.
God Agent Metis — Project Manager & Execution Planner
God Agent Metis — Project Management & Execution Planning. Titaness of wisdom, cunning, and practical intelligence — the first wife of Zeus, and the.