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/tandnguyendev/dev-workflow/rollbacknpx skills add tandnguyendev/dev-workflow --skill rollbackgit clone --depth 1 https://github.com/tandnguyendev/dev-workflowWhat 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 | $0.00050 | $0.00500 |
| Opus 5 | $0.00025 | $0.00250 |
| Sonnet 5 | $0.00010 | $0.00100 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
rollback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Restore the working tree to a checkpoint, undoing recent agent changes. This is
safe: it first saves the current state as a reversible pre-rollback checkpoint,
never moves your branch/HEAD, and never hard-deletes anything from git.
The CLI is python3 "${CLAUDE_SKILL_DIR}/../../hooks/checkpoint.py" <cmd> (this
resolves to the plugin's hooks/checkpoint.py).
Steps:
- If the user did NOT name a checkpoint, first list them and show the user so
they can confirm the target (default = most recent non-
pre-rollbackcheckpoint):python3 "${CLAUDE_SKILL_DIR}/../../hooks/checkpoint.py" list - Perform the rollback (pass the chosen ref, or omit for the default):
This step is intentionally NOT pre-approved — because a rollback rewrites the working tree, Claude Code will ask the user to permit this exact command. That confirmation is expected; wait for it.python3 "${CLAUDE_SKILL_DIR}/../../hooks/checkpoint.py" rollback [ref]undois not pre-approved either: it is itself a rollback (to thepre-rollbackcheckpoint) and rewrites the working tree just the same, so it gets the same confirmation. Onlylistis read-only. - Relay the tool's output verbatim, including how to reverse it:
Also note that files CREATED since the checkpoint are left in place (they show up inpython3 "${CLAUDE_SKILL_DIR}/../../hooks/checkpoint.py" undogit status) and can be removed manually if unwanted.
Only meaningful in a git repository. If the CLI prints "not a git repository" or
"no checkpoints", relay that and stop. Do not attempt manual git reset/checkout
yourself — always go through the CLI so the operation stays safe and reversible.
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 · 40 lines · 50 tokens per session scan A c153af7f18b4
rollback is a skill published in the GitHub repository tandnguyendev/dev-workflow (2 stars, last pushed 7d ago), licensed MIT. It adds 50 tokens to every session and 500 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…