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 drafthq/draft --skill revertgit clone --depth 1 https://github.com/drafthq/draftWrote 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/drafthq/draft/revert)<a href="https://agentmods.dev/skills/drafthq/draft/revert"><img src="https://agentmods.dev/badge/skills/drafthq/draft/revert/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/drafthq/draft/revert"><img src="https://agentmods.dev/badge/skills/drafthq/draft/revert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 17 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00066 | $0.01494 |
| Opus 5.5 | $0.00026 | $0.00598 |
| Sonnet 5.5 | $0.00013 | $0.00299 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
revert 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Revert
Perform intelligent git revert that understands Draft's logical units of work.
Red Flags - STOP if you're
- Reverting without showing preview first
- Skipping user confirmation
- Not checking for uncommitted changes first
- Reverting more than requested
- Not updating Draft state after git revert
- Assuming you know which commits to revert without checking
Preview and confirm before any destructive action.
Step 0: Pre-flight Check
-
Verify Draft context exists:
ls draft/tracks.md 2>/dev/nullIf
draft/does not exist: STOP — "No Draft context found. Run/draft:initfirst." -
Check working tree: Run
git status --porcelain. If output is non-empty, warn the user about uncommitted changes and suggest stashing or committing first. Do NOT proceed until working tree is clean.
Step 1: Analyze What to Revert
Ask user what level to revert:
- Task - Revert a single task's commits
- Phase - Revert all commits in a phase
- Track - Revert entire track's commits
If user specifies by name/description, find the matching commits.
Step 2: Find Related Commits
Primary method: Read plan.md — every completed task has its commit SHA recorded inline. Use these SHAs directly.
If no commits found (all tasks are [ ] Pending with no SHAs): announce "No commits found for this scope — nothing to revert." and STOP.
Fallback method (if SHAs missing but completed tasks exist): Search git log by track ID pattern:
For Draft-managed work, commits follow pattern:
feat(<track_id>): <description>fix(<track_id>): <description>test(<track_id>): <description>refactor(<track_id>): <description>
# Find commits for a track
git log --oneline --grep="<track_id>"
# Find commits in date range (for phase)
git log --oneline --since="<phase_start>" --until="<phase_end>" --grep="<track_id>"
Cross-reference: Verify SHAs from plan.md match the git log results. Git log is always authoritative for commit identification. plan.md is authoritative for task-to-commit mapping. On SHA mismatch, prefer git log and warn the user.
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 First seen · 185 lines · 66 tokens per session scan A 6c425808c301
revert is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 9d ago), licensed MIT. It adds 66 tokens to every session and 1,494 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 2026-08-30.
Other skills, from other repositories
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
branch-pr
Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
chained-pr
Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.