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 instructions/rjmurillo/ai-agents/plugin-version-bumpgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/instructions/rjmurillo/ai-agents/plugin-version-bump)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/plugin-version-bump"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/plugin-version-bump.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00764 | $0.00764 |
| Opus 5 | $0.00382 | $0.00382 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00076 | $0.00076 |
Grade A, and why
ai-agents plugin-version-bump.instructions.md 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Manifests Carry No Version
None of the three packaged plugin manifests carries a version field, and a PR
must never add one back:
.claude/.claude-plugin/plugin.jsonsrc/copilot-cli/.claude-plugin/plugin.jsonsrc/claude/.claude-plugin/plugin.json
build/scripts/validate_plugin_version_bump.py fails with exit 1 when any of
them carries the key. The two marketplace files
(.claude-plugin/marketplace.json, .github/plugin/marketplace.json) must stay
version-free for the same reason; a test in
tests/build_scripts/test_validate_plugin_version_bump.py fails if a version
appears in either.
Why
Claude Code resolves plugin freshness from the first of these that is set:
plugin.json version, then the marketplace entry version, then the git
commit SHA of the plugin's source for relative-path sources in a git-hosted
marketplace. All three plugins here ship from relative-path sources, so with the
field absent every plugin resolves to the commit SHA, which changes on every
merge. That is per-commit freshness with no human step.
Adding the field back does two bad things at once. It switches Claude Code to the explicit-version path, where pushing new commits without bumping the field has no effect. And it re-creates a single line that every plugin-source PR has to write, so any two such PRs conflict pairwise: issue #4080 measured 14 of 22 conflicting PRs conflicting on nothing but that line, and merging #4077 immediately re-conflicted the next four green PRs.
GitHub Copilot CLI lists version under optional metadata, with name as the
only required field, and its shipped update path calls updatePlugin
unconditionally.
See ADR-092, which supersedes ADR-079.
What a PR does now
Nothing. Do not touch the manifests when you change plugin content. There is no bump, no parity pairing, and no rebase recipe, because there is no version line to collide on.
If you are rebasing an older branch that still carries a bump hunk, you will hit
a conflict on the version line exactly once: git reports CONFLICT (content)
with the incoming side empty. Take the empty side. The
gate enforces it: keeping the line leaves a manifest carrying version, and the
gate fails that on your branch before merge.
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 · 76 lines · 764 tokens per session scan A cd81f5c763c7
ai-agents plugin-version-bump.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 764 tokens to every session, about $0.0038 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 2026-09-03.
Other instructions, from other repositories
abtars AGENTS.md
Instructions for aksika/abtars, covering agents.md, quick commands, architecture, model-call chokepoint: spin(spec) (#1271) and external dependency: abmind.
Alex_Skill_Mall mall-maintenance-rules.instructions.md
Always-on routing for Mall maintenance work — fires the right Mall skill at the right moment. Distinguishes Mall-owned automation from out-of-scope editorial work.
gameforge AGENTS.md
Instructions for robcost/gameforge, covering general guidelines for working with nx, scaffolding & generators and when to use nxdocs.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.