resolve-todos

resolve-todos is a command for Claude Code from JairoTorregrosa/jaiskills. It costs 18 tokens per session (851 once invoked), scanned A, original, MIT.

A command that assigns approved TODO items to separate worker agents, while ordering them around their dependencies. A TODO is a written work item, and dependencies are other items that must be finished first.

In plain words
What is it for?
Use it to load ready TODO files, group them into execution waves, run independent items in parallel, and mark completed items.
Why use it?
It removes the need to resolve each approved work item manually and avoids starting dependent work too early. It stops if the TODOs contain a circular dependency.

Command for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the jaiskills plugin — 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server shipped together

Good fit Use it to load ready TODO files, group them into execution waves, run independent items in parallel, and mark completed items.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/jairotorregrosa/jaiskills/resolve-todos
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.

Clone the repo
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskills

Made for: Claude Code.

Or install jaiskills, the plugin that ships this one along with the rest of its 12 skills, 13 commands, 4 agents, 2 hooks, 1 MCP server.

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 resolve-todos

README.md
[![agentmods](https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/resolve-todos/github.svg)](https://agentmods.dev/commands/jairotorregrosa/jaiskills/resolve-todos)
Your own site
<a href="https://agentmods.dev/commands/jairotorregrosa/jaiskills/resolve-todos"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/resolve-todos/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 resolve-todos

Your own site · 80×15
<a href="https://agentmods.dev/commands/jairotorregrosa/jaiskills/resolve-todos"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/resolve-todos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00018 $0.00851
Opus 5 $0.00009 $0.00426
Sonnet 5 $0.00004 $0.00170
Haiku 4.5 $0.00002 $0.00085

Measured 11d ago against content hash 2b78a1112e47, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

resolve-todos 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 11d 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.

commands/resolve-todos.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve Approved TODOs

Spawn parallel worker agents to resolve all ready TODOs. Each worker reads its assigned TODO, implements the recommended action, and marks it complete.

Steps

1. Load Ready TODOs

Read all todos/*-ready-*.md files using Glob.

If an argument was provided (e.g., a specific ID like 003 or a pattern like p1), filter to only matching files.

If no ready TODOs found, tell the user: "No ready TODOs to resolve. Run /jaiskills:triage first to approve pending findings."

2. Parse Dependencies

For each ready TODO, read the dependencies field from YAML frontmatter. Dependencies reference other TODO IDs (e.g., ["001", "005"]).

3. Group into Waves

Compute execution waves based on dependencies (same algorithm as plan wave computation):

  • Wave 1: TODOs with no dependencies (or whose dependencies are already complete)
  • Wave 2: TODOs that depend on Wave 1 items
  • Wave N: TODOs that depend on Wave N-1 items

If circular dependencies are detected, report to the user and stop.

4. Execute Waves

For each wave, spawn parallel jaiskills:insistir-worker agents — one per TODO:

Task tool:
  name: "todo-resolver-{id}"
  subagent_type: "jaiskills:insistir-worker"
  prompt: |
    ## Context
    You are resolving a TODO from a review finding.

    ## Your Task
    Read the TODO file at: todos/{id}-ready-{priority}-{description}.md

    Implement the fix described in the **Recommended Action** section.
    Follow the **Acceptance Criteria** checklist — all items must pass.

    After implementation:
    1. Run any relevant validation (tests, typecheck, lint)
    2. Stage and commit with message: "fix: resolve todo {id} - {description}"
    3. Report completion to the lead via SendMessage

5. Mark Complete

After each worker completes and is shut down:

  1. Rename the file from ready to complete:
    mv todos/{id}-ready-{priority}-{desc}.md todos/{id}-complete-{priority}-{desc}.md
    
  2. Update the status field in YAML frontmatter from ready to complete
  3. Update the updated date in frontmatter
  4. Append to the Work Log section with what was done:
    ### YYYY-MM-DD
    - Resolved by worker agent
    - Changes: [files modified from worker's report]
    - Commit: [commit hash]
    

Read the full file on GitHub · 104 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. 11d ago First seen · 104 lines · 18 tokens per session scan A 2b78a1112e47

Subscribe to this mod's changes

resolve-todos is a command published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 10d ago), licensed MIT. It adds 18 tokens to every session and 851 once invoked, about $0.0001 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.