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 aaronartistzhang-afk/DailyWork --skill change-triagegit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote 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/aaronartistzhang-afk/dailywork/change-triage)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/change-triage"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/change-triage/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/aaronartistzhang-afk/dailywork/change-triage"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/change-triage.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 | $0.00224 | $0.01381 |
| Opus 5 | $0.00112 | $0.00691 |
| Sonnet 5 | $0.00045 | $0.00276 |
| Haiku 4.5 | $0.00022 | $0.00138 |
Grade A, and why
change-triage 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 12d 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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
change-triage — a "is it worth doing?" decision table
Turn "here's what we could do" into "do this now / this goes to backlog / skip this" — and the human makes the call.
Core rule: a recommendation without its cost is not acceptable. Every row must answer "what happens if we don't?", and the answer has to be the concrete harm happening now, not "there might be a risk."
This is the table form of one principle: when you propose a change, you must state the cost of not doing it. This skill gives that principle a fixed shape so it can't be skipped.
When to use
- The human asks whether something is worth it: what breaks if we don't fix it / what's the necessity / I can't decide between these.
- The human wants each backlog item's necessity and risk laid out.
- The only condition for entering this on my own initiative: I am about to propose ≥2 optional changes, and I need the human to decide scope / cost / priority.
Not for:
- Judging correctness → that's a review-gate job. A gate judges "is it right?"; this table answers "is it worth it?" — two different questions.
- A single obviously-must-fix bug → just fix it, don't pop a seven-column table.
- Pure ordering with no cost question (a bare "which first?" when there's no candidate list in context) → ask what the candidates are first; don't invent a table.
⚠️ Don't pop the table for every issue you spot. A seven-column table for one obvious fix reads as noise, not help.
The fixed table (seven columns, none may be dropped)
| Item | Concrete harm now (with evidence) | What fixing it buys | Cost (blast radius + review rounds) | Improves quality? | Evidence strength of this call | Recommended tier (do now / backlog / skip) |
|---|---|---|---|---|---|---|
| <what already happened, with path/date/count> | <how many files + expected review rounds> | yes / no | measured / read the code / inferred / unverified | do now / backlog / skip |
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.
- 12d ago First seen · 78 lines · 224 tokens per session scan A 12faf2b10533
change-triage is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 14d ago), licensed MIT. It adds 224 tokens to every session and 1,381 once invoked, about $0.0011 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 skills, from other repositories
task-list
Required for 4+ step requests; add tasks at start and update status after each step.
auditing-endpoints
Audit every endpoint in a PostHog project for staleness, failed materialisations, and unused materialised versions. Use when the user asks "what endpoints can I clean up?", "are any of my endpoints broken?", "which materialised versions are still being called?", or wants a one-shot cleanup pass over the Endpoints…
stacking-prs
Create and manage GitHub native Stacked PRs in this repo with the gh stack CLI. Use when asked to stack PRs, split a large change into a stack, add a layer to a stack, restack or rebase a stack, adopt existing branches or PRs into a stack, check out someone else's stack, or land a stack. Covers creating and submitting…
managing-endpoint-versions
Work safely with endpoint versions — preview a draft in the playground, roll back to an older version, update settings on one version without bumping query history, deactivate a specific version. Use when the user asks "how do I roll back my endpoint", "preview my changes before publishing", "I want to fix v5 without…
setting-up-support-slack-locally
Connect a real Slack workspace to local PostHog Conversations (the SupportHog Slack app) so Slack messages become support tickets and replies post back. Use when the user wants to test the conversations Slack integration locally, hits "Support Slack OAuth client ID is not configured", gets a white screen or "Network…
eol-process
Run a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.