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 wahidyankf/ose-public --skill repo-maintaining-task-listsgit clone --depth 1 https://github.com/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/repo-maintaining-task-lists)<a href="https://agentmods.dev/skills/wahidyankf/ose-public/repo-maintaining-task-lists"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/repo-maintaining-task-lists/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/wahidyankf/ose-public/repo-maintaining-task-lists"><img src="https://agentmods.dev/badge/skills/wahidyankf/ose-public/repo-maintaining-task-lists.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 | $0.00049 | $0.00645 |
| Opus 5.5 | $0.00020 | $0.00258 |
| Sonnet 5.5 | $0.00010 | $0.00129 |
| Haiku 4.5 | $0.00005 | $0.00064 |
Grade A, and why
repo-maintaining-task-lists 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Maintaining Task Lists
Delegated agents do not inherit the canonical instruction file. This Skill is how the task-list obligation reaches them, and it binds a delegated agent exactly as it binds the main thread.
The Obligation
Before any task — including a purely conversational one — create, update, or adjust the harness's native task list. The list is opened before the work starts, not reconstructed after it finishes.
There is no step-count threshold. A one-line edit, a rename, and a question answered in prose all open or adjust an entry. A threshold would ask you to estimate the work before recording it, at exactly the moment that estimate is least reliable.
Standards
- Create before executing. The primary phases are recorded before the first tool call. The list need not be exhaustive at the start — it grows as work proceeds.
- Mark in-progress before starting. A task reading
pendingwhile its work is underway is a stale list, which is a defect rather than a minor gap. - Mark completed immediately after verification. Completion means the stated outcome exists and has been confirmed — not that it ought to be done by now.
- Add discovered tasks on the spot. A follow-up that is not recorded is invisible.
- One task per concrete outcome. Split bundled work before starting it.
- Preserve active rule decisions. Immediately record every unsuperseded user-established repository-rule decision constraining the work with its operative statement, scope, source, and status. Reproduce active entries in every compaction summary and handoff. Before the first action after restored context or continuation, re-read canonical instructions and reconcile the record; stop and report any unresolved conflict.
What Does Not Satisfy This
- A list written after the work, describing what already happened.
- Prose narration of progress in place of list entries.
- A list created at the start and never updated again.
Harness Note
What ships with it
1 file 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.
- 2d ago First seen · 55 lines · 49 tokens per session scan A 784adac780a9
repo-maintaining-task-lists is a skill published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 645 once invoked, about $0.0002 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 2026-10-14.
Other skills, from other repositories
nx-plugin-for-aws
Scaffold and build cloud-native applications on AWS using @aws/nx-plugin generators. Use when the user wants to create workspaces, generate projects, or scaffold infrastructure with the Nx Plugin for AWS.
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
implement
Implement an agreed issue or spec through implementation, review, fixes, and a PR ready to merge.
taskwarrior
Use when querying or modifying tasks via the taskwarrior CLI - dense recipes for listing, single-field lookups, multi-task batched lookups, full-text search, and the soft description-length convention. Activates on task list, task add, task info, task done, "what's on the backlog", "find a task", or any taskwarrior…
weekly-brief
Assemble a short Monday briefing across sales, finance, hiring and files from live workspace data. Use for weekly summaries, standup notes, or "what changed last week".
suggest-automations
Offer the three most common automations for a user as a single-choice card, from your own knowledge of their team and their apps, then build the one they choose once they confirm, or offer more. The system preloads it on onboarding threads, where the opening card already asked the user about themselves. Use it on…