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 agentmods add skills/drafthq/draft/revertnpx skills add drafthq/draft --skill revertgit clone --depth 1 https://github.com/drafthq/draftWhat 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 | $0.00066 | $0.01494 |
| Opus 5 | $0.00033 | $0.00747 |
| Sonnet 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 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 — 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.
- 2d 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 14d ago), licensed MIT. It adds 66 tokens to every session and 1,494 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
save-progress
Save current project task progress to local task state file for cross-session continuity. Use when the user asks to save progress, uses an equivalent localized trigger phrase, the session is interrupted, or the user wants to resume work later. Writes to .claude/project-task-state.json so next session can load it via…
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.