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/agent-marketplace-kit/cli/bumpgit clone --depth 1 https://github.com/AGent-marketplace-KIT/cliWhat 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 | $0.00012 | $0.00722 |
| Opus 5 | $0.00006 | $0.00361 |
| Sonnet 5 | $0.00002 | $0.00144 |
| Haiku 4.5 | $0.00001 | $0.00072 |
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 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agmk bump
Bump a local plugin's version — automatically from conventional commits, or to an explicit level — then propagate the change to the catalog, docs, and any built registries.
agmk bump [plugin] [level] [options]
Arguments
| Argument | Description |
|---|---|
[plugin] |
Plugin name. Prompted if omitted. |
[level] |
major | minor | patch | auto. Default auto. |
Options
| Option | Description |
|---|---|
-t, --tag |
Commit the bump and create the release tag <plugin>@<version>. |
--dry-run |
Show what would change without writing anything. |
How auto chooses a level
agmk inspects the commits that touch the plugin's directory, made since
its last <plugin>@x.y.z tag, and applies conventional-commit rules:
| Commits contain | Level | Example |
|---|---|---|
a breaking change (feat!:, BREAKING CHANGE:) |
major | 0.2.1 → 1.0.0 |
a feat: (no breaking) |
minor | 0.2.1 → 0.3.0 |
only other types (fix:, chore:, …) |
patch | 0.2.1 → 0.2.2 |
If there are no qualifying commits, auto reports "nothing to bump". The
current version defaults to 0.1.0 when the manifest has none.
What it writes
- the new
versioninplugins/<plugin>/.claude-plugin/plugin.json; - a dated, newest-on-top entry in
plugins/<plugin>/CHANGELOG.md, built from the analysed commit subjects; - an internal
sync, propagating the version tomarketplace.json, the README plugin table, theAGENTS.mdlist, and any built Codex/Cursor registries.
With --tag it then stages all changes, commits them as
chore(release): <plugin>@<version>, and creates the tag <plugin>@<version>
(push with git push --follow-tags). That tag is the boundary the next auto
bump measures from.
Examples
agmk bump tdd-coach --dry-run # preview the auto level and version
agmk bump tdd-coach # bump + changelog + sync
agmk bump tdd-coach minor # force a minor bump
agmk bump tdd-coach --tag # bump, then commit + tag the release
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 · 75 lines · 12 tokens per session scan A f23e2cea80c3
bump is a command published in the GitHub repository AGent-marketplace-KIT/cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 12 tokens to every session and 722 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 2026-08-31.
Other commands, from other repositories
annotate-plan
Draft a plan and open it in the annotator UI for user review.
docs
Command "docs" from tilework-tech/nori-skillsets, covering noridoc: commands, how it fits into the larger codebase, core implementation and things to know.
build-loop
Planning Mode — scaffold a target project's l00prite/ folder (CLAUDE.md blueprint, AGENTS.md, .l00prite memory, universal loop prompts), root pointer files, vendor adapters, and a skeleton repo from a project idea. Stops after scaffolding; --execute hands off to Execution Mode only through execute-loop's confirmed…
event-loop
You are processing one pending l00prite event. Events are protocol objects, not vendor-specific automation commands.
respond-to-review
You are responding to one review-related l00prite event. Treat .l00prite/ as the shared source of truth across agents.
resume-loop
You are resuming a l00prite-managed project. Treat .l00prite/ as the shared source of truth across Claude, Codex, GPT, Gemini, and future agents.