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 skills add JairoTorregrosa/jaiskills --skill file-todosgit 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/skills/jairotorregrosa/jaiskills/file-todos)<a href="https://agentmods.dev/skills/jairotorregrosa/jaiskills/file-todos"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/file-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/skills/jairotorregrosa/jaiskills/file-todos"><img src="https://agentmods.dev/badge/skills/jairotorregrosa/jaiskills/file-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 | $0.00184 | $0.01267 |
| Opus 5.5 | $0.00074 | $0.00507 |
| Sonnet 5.5 | $0.00037 | $0.00253 |
| Haiku 4.5 | $0.00018 | $0.00127 |
Grade A, and why
file-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 1mo 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
File-based TODO lifecycle
Track review findings and work items as individual markdown files in todos/ at the project root. Each file carries the full context (problem, evidence, proposed solutions, work log) so any agent can pick it up and resolve it independently. Adapted from EveryInc's compound-engineering plugin (https://github.com/EveryInc/compound-engineering-plugin).
Request: $ARGUMENTS
Modes
Pick the mode from the request (when $ARGUMENTS is empty, the user's latest message is the request):
| Request | Mode | Read |
|---|---|---|
triage [filter], "triage / review the pending todos" |
Present each pending TODO for a user decision. Decision-only: never write code in this mode. | references/triage.md |
resolve [ids or filter], "fix / resolve the approved todos" |
Spawn parallel workers over ready TODOs in dependency waves; each edits and commits. Run only when the user asks for it. |
references/resolve.md |
| Findings, review output, "file these as todos" | Create one TODO per finding (Operations below). | references/todo-template.md |
| Nothing specific | Report counts by status and priority, then offer the next step (triage if anything is pending, resolve if anything is ready). | — |
Lifecycle: create (pending) → triage (ready or deleted) → resolve (complete).
Naming convention
{id}-{status}-{priority}-{description}.md
| Segment | Format | Example |
|---|---|---|
id |
3-digit zero-padded | 001, 042, 100 |
status |
pending, ready, complete |
pending |
priority |
p1, p2, p3 |
p1 |
description |
kebab-case, max 50 chars | missing-auth-middleware |
Full example: 001-pending-p1-missing-auth-middleware.md
Statuses
| Status | Meaning |
|---|---|
pending |
Created from review findings. Needs triage; no decision made yet. |
ready |
Approved by the user during triage. Ready to be worked on. |
complete |
Work finished. Issue resolved and verified. |
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · +16 lines · +41 tokens per session 6d215d2232b0
- 1mo ago First seen · 97 lines · 143 tokens per session scan A 6b702ecbca9b
file-todos is a skill published in the GitHub repository JairoTorregrosa/jaiskills (10 stars, last pushed 4d ago), licensed MIT. It adds 184 tokens to every session and 1,267 once invoked, about $0.0007 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 skills, from other repositories
help
Get oriented with the solopreneur plugin — see your AI team, check project status, and get suggestions for what to do next. Use when you're getting started or need a refresher.
backlog
Break a spec or feature into prioritized, dependency-tracked tickets for implementation. Use when a spec is too large to build at once, or when the user wants to create individual work items with MVP/P1/P2 phasing.
sprint
Execute a batch of backlog tickets in parallel. Use when the user wants to build multiple unblocked tickets simultaneously with integrated QA review.
standup
Generate a daily standup summary showing what was done, what is planned, and any blockers. Use when the user wants a status update or progress report.
fabric-swarm
Creates a self-organizing team of persistent Pi Fabric actors with durable topics, mailboxes, and compare-and-swap tasks. Use for messenger-like collaboration and long-lived delegated work.
loom-usage
Meta-orchestration skill for Claude driving loom itself.