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 Unique-Divine/jiyuu --skill md-tasksgit clone --depth 1 https://github.com/Unique-Divine/jiyuuWrote 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/unique-divine/jiyuu/md-tasks)<a href="https://agentmods.dev/skills/unique-divine/jiyuu/md-tasks"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/md-tasks/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/unique-divine/jiyuu/md-tasks"><img src="https://agentmods.dev/badge/skills/unique-divine/jiyuu/md-tasks.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 | $0.00082 | $0.00883 |
| Opus 5.5 | $0.00033 | $0.00353 |
| Sonnet 5.5 | $0.00016 | $0.00177 |
| Haiku 4.5 | $0.00008 | $0.00088 |
Grade A, and why
md-tasks 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 16d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown tasks and checkbox conventions
Follow these conventions so agents and humans can scan open work reliably.
Usage guidelines
Checkbox notation
Denote open tasks or TODOs with standard checkbox notation:
- [ ]for incomplete tasks.- [x]for done tasks.
Indentation defines subtasks: extra leading spaces nest bullets under a parent item.
In planning/spec documents, default every actionable item at every nesting level to checkbox notation. Do not hide implementation work in ordinary bullets.
Often add ordinary sub-bullets for status or context beneath a task, but only when the bullet is not itself work to do. For example:
- [ ] Some task
- Status: maybe some status description or how it was completed
- More context
- [ ] Subtask A
This keeps review tight: unfinished work sorts visually to checklist lines while still allowing narrative detail.
Actionable sub-bullets
If a sub-bullet describes work to do, a decision to resolve, behavior to implement, a file to create, a test to add, or an acceptance criterion to verify, write it as a checkbox task too:
- [ ] Implement tx archive CLI.
- [ ] Keep Bash responsible for chain config, keyring preflight, and broadcast.
- [ ] Make TypeScript responsible for txhash parsing and Markdown formatting.
- Rationale: TypeScript is easier to test for JSON, filenames, and CLI args.
Use ordinary nested bullets only for non-actionable context, rationale, status,
examples, or notes. When unsure whether a sub-bullet is actionable, prefer
- [ ].
Task Questions
Sometimes we'll pose a question or frame a resolve decision as a task. That can look like this.
- [ ] Q: Some open question?
A: Once resolved, replace this question with a plain decision note and open
tasks for its actionable consequences.
Decisions and implementation tasks
Deciding what to do and doing it are different things. During specification, an
unresolved decision may be an open task. Once resolved, replace that task with
a plain decision note. Put its concrete consequences immediately beneath it as
unchecked tasks. Do not mark a decision [x] merely because the user answered
the question.
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.
- 16d ago Changed · +3 lines d632d3375012
- 1mo ago First seen · 112 lines · 82 tokens per session scan A 34ba3a37bc4a
md-tasks is a skill published in the GitHub repository Unique-Divine/jiyuu (6 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 883 once invoked, about $0.0003 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
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
migrate-goldmark-extension-v1-to-v2
Migrate goldmark extension from goldmark v1 to v2.
go
Use when writing, reviewing, testing, or shipping Go code and HTTP services: idioms, %w error wrapping, goroutine/context/errgroup concurrency, net/http 1.22 routing, log/slog, project layout, table-driven tests, Go hardening. NOT language-agnostic threat modeling (that is secure-coding), NOT Dockerfile/CI shipping…
pi-loop-forensics
Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.
nightly-session-watch
Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real prompt-token spend, and whether the observation and palace pipelines are still recording. Triages each finding to the specialist skill that diagnoses it. Use for an unattended daily health check, or on…
tui-render-debug
Diagnose and fix pi-go TUI rendering corruption, especially displaced panels, stale rows, cursor drift, and terminal-specific ANSI incompatibilities.