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 martinemde/dotfiles --skill work-ongit clone --depth 1 https://github.com/martinemde/dotfilesWrote 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/martinemde/dotfiles/work-on)<a href="https://agentmods.dev/skills/martinemde/dotfiles/work-on"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/work-on/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/martinemde/dotfiles/work-on"><img src="https://agentmods.dev/badge/skills/martinemde/dotfiles/work-on.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 6 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 191 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 193 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 195 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 196 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 197 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 198 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00033 | $0.00685 |
| Opus 5.5 | $0.00013 | $0.00274 |
| Sonnet 5.5 | $0.00007 | $0.00137 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
work-on 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work On
Orchestrate a GitHub issue from understanding through pull request. Preserve existing work, follow the active repository instructions, and adapt to the task and workflow facilities supplied by the current harness.
Supporting files
- Read TIERS.md for the complexity decision matrix.
- Read EPIC-WORKFLOW.md before decomposing an epic.
Constraints
- Always assess the tier before starting implementation.
- Use only skills and agents available in the current harness. Perform an equivalent step inline when no matching capability exists.
- Proceed autonomously except for genuine blockers or decisions that materially change scope.
- Use the
commitskill, when available, for each logical change. - Preserve any task list created by the current harness. Do not overwrite unrelated user work.
Workflow
1. Fetch and assess
Fetch the issue and read its discussion:
gh issue view <id-or-url> --json number,title,body,labels,comments,assignees,milestone
Classify it as Quick fix, Small, Medium, Large, or Epic using TIERS.md. State the tier and the evidence for it.
2. Build a tailored runbook
Use the following sequences as defaults. Skill names are shown without harness-specific invocation syntax.
- Quick fix: checkout, edit, commit, pull request.
- Small: checkout, gather-context at light scope, edit, commit, pull request.
- Medium: checkout, gather-context, think, plan, review-plan, share-plan, implement, simplify, commit, pull request.
- Large: the Medium flow with parallel workstreams where useful, incremental commits, and reflect after the pull request.
- Epic: gather-context, think about decomposition, split into independently verifiable units, run the appropriate tier flow for each unit, coordinate integration, and reflect.
Tell the user the selected sequence, key dependencies, and any human checkpoints. Then continue unless a checkpoint is required by repository policy.
What ships with it
2 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.
- 5d ago Changed · -150 lines · +33 tokens per session 28ef4f74e8d4
- 1mo ago First seen · 220 lines · 0 tokens per session scan A 475b4f4a444a
work-on is a skill published in the GitHub repository martinemde/dotfiles (10 stars, last pushed 2d ago), licensed ISC. It adds 33 tokens to every session and 685 once invoked, about $0.0001 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
issue-work
Pick up an existing GitHub issue in the checked-out repo — implement from scratch or take over an in-flight PR. Use when asked to work, take, implement, fix, or close issue.
issue-create
File a new GitHub issue in the checked-out repo — search first for duplicates/adjacent issues to update or reference, detect the repo's issue template if any, then compose title/body/labels/milestone matching house style. Use when asked to file, create, open, report, or track an issue.
github-issues
Manage GitHub issues with gh: confirm repo and state, deduplicate, preserve evidence, and verify authorized creation, edits, labels, comments, or closure.
project-backlog
Turn audit findings into deduplicated, prioritized issue drafts with dependencies and explicit authorization before GitHub mutation.
autopilot
Carry a well-scoped GitHub issue through the full dev loop autonomously, stopping at a per-run tier boundary (PR-ready, or merge+deploy for small reversible changes).
autopilot-triage
Vet open issues for autonomous resolution and queue the qualifying ones with the autopilot-queued label — the start-of-day "fill the queue" half of the triage → run split.