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 commands/xiaolai/vmark/bumpgit clone --depth 1 https://github.com/xiaolai/vmarkWhat 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 | $0.00018 | $0.01364 |
| Opus 5 | $0.00009 | $0.00682 |
| Sonnet 5 | $0.00004 | $0.00273 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
bump 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 yesterday.
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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Bump
Bump the version number across all 5 required files, land the commit on main
through a pull request, then tag and push.
main cannot be pushed directly (since 2026-07-27 — enforce_admins: true
on the frontend + rust checks, see .claude/rules/60-ai-governance.md §10).
A direct push of the bump commit is rejected, because the required checks cannot
have run on a commit the remote has never seen. Tag pushes are not gated, so
the release trigger is unchanged.
Input
$ARGUMENTS
Phase 1: Determine New Version
Read current version from package.json.
Parse $ARGUMENTS:
| Input | Action |
|---|---|
0.5.0 |
Use exactly as specified |
patch |
Increment patch: 0.4.2 → 0.4.3 |
minor |
Increment minor: 0.4.2 → 0.5.0 |
major |
Increment major: 0.4.2 → 1.0.0 |
| (empty) | Default to patch |
Validate the resolved version matches ^[0-9]+\.[0-9]+\.[0-9]+$. Anything
else (e.g., 0.7.14.1, 0.7, v0.7.15) is rejected — the Tauri updater
parses latest.json.version with semver and rejects non-canonical
shapes, and any divergence between the five files breaks the build.
Display: Current: {old} → New: {new} and ask user to confirm.
Phase 2: Quality Gate
Run pnpm check:all before touching any version file. Abort the bump
on any failure — tagging a broken build creates a public tag that the
release workflow then fails on, and the tag stays in the repo until
manually deleted.
Phase 3: Update All 5 Files
All five files must be updated — see .claude/rules/40-version-bump.md.
| File | Field |
|---|---|
package.json |
"version" |
src-tauri/tauri.conf.json |
"version" |
src-tauri/Cargo.toml |
version |
server/mcp/package.json |
"version" |
server/mcp/src/cli.ts |
const VERSION |
Use the Edit tool for each file — not sed.
Then sync the derived lockfile, which is a sixth file in the commit even though nothing edits it by hand:
cargo update -p vmark --manifest-path src-tauri/Cargo.toml
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.
- yesterday First seen · 138 lines · 18 tokens per session scan A 961b6ba50c0d
bump is a command published in the GitHub repository xiaolai/vmark (544 stars, last pushed 2d ago), licensed ISC. It adds 18 tokens to every session and 1,364 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.