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.
git clone --depth 1 https://github.com/JairoTorregrosa/jaiskillsWrote 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/commands/jairotorregrosa/jaiskills/resolve-todos)<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.
<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>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 | $0.00018 | $0.00851 |
| Opus 5 | $0.00009 | $0.00426 |
| Sonnet 5 | $0.00004 | $0.00170 |
| Haiku 4.5 | $0.00002 | $0.00085 |
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.
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:
- Rename the file from
readytocomplete:mv todos/{id}-ready-{priority}-{desc}.md todos/{id}-complete-{priority}-{desc}.md - Update the
statusfield in YAML frontmatter fromreadytocomplete - Update the
updateddate in frontmatter - 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]
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.
- 11d ago First seen · 104 lines · 18 tokens per session scan A 2b78a1112e47
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.
Other commands, from other repositories
speckit.check-integration
Validates that tasks.md considers existing codebase implementations and integration opportunities before execution. Use when you need to check task alignment with the current codebase.
lavra-work-teams
Work on multiple beads with persistent worker teammates that self-organize through a ready queue.
lavra-retro
Weekly retrospective with shipping analytics, team performance, and knowledge synthesis.
lavra-ship
Fully automated ship sequence from code-ready to PR-open with beads closed and knowledge captured.
lavra-work-ralph
Autonomous retry mode for bead work -- iterates until completion criteria are met or retry budget is exhausted.
lavra-import
Import a markdown plan into beads as an epic with child tasks.