Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/bostonaholic/teamnpx agentmods add skills/bostonaholic/team/version-bumpWrote 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/skills/bostonaholic/team/version-bump)<a href="https://agentmods.dev/skills/bostonaholic/team/version-bump"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/version-bump/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/bostonaholic/team/version-bump"><img src="https://agentmods.dev/badge/skills/bostonaholic/team/version-bump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 19 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 37 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 311 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 323 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 329 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 5.1 | $0.00042 | $0.03487 |
| Opus 5.5 | $0.00017 | $0.01395 |
| Sonnet 5.5 | $0.00008 | $0.00697 |
| Haiku 4.5 | $0.00004 | $0.00349 |
Grade A, and why
version-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 13d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Version Bump — version a project at land time
This repository's own versioning procedure. AGENTS.md declares it as the
pre-merge step, so the land command runs it before merging. Tagging and the
GitHub release are not part of it; release-on-merge.yml does that on
merge. When invoked directly, run this skill before the land command,
against the version of main you intend to land onto. When a land command
invokes this skill, return to it after step 8.
Precondition — explicit land intent
Why: the bump is computed against the base branch's tip at this moment; a bump made before the land goes stale when another PR merges, and the pre-merge guard then denies the merge.
This skill fires only on explicit land intent, meaning one of:
- The user asked to land: "ship it", "land the PR", "land this".
- The user asked for the bump itself: "bump the version", "version this PR".
- A land command is already in flight and reached the project's pre-merge steps.
Never infer land intent. None of the following is a cue to bump:
- The work is finished, the review passed, or CI is green.
- A draft PR is about to be opened, or was just opened. A drafted PR carries
no version: the bullet goes under
## [Unreleased]and nothing else moves. - The invariant script exited 1. That exit states a precondition for merging, expected for a runtime PR's whole review lifetime, never a request to bump now.
With no land intent, stop and say so. Report that the branch will need a bump before it can merge, and wait for the user. Do not bump "to be helpful".
Steps
0. Runtime-vs-dev gate — does this PR warrant a bump at all?
Run this before everything else. Most steps below only apply if it says yes.
The quick look is orientation only — it never decides the exit:
git diff "origin/<default>...HEAD" --name-only. The decision comes from the
invariant run, the same invocation contract the pre-merge guard enforces:
- Resolve the default branch by asking GitHub (
gh repo view), falling back to the localorigin/HEADref. Never a guessedmain. If both fail, stop: no verdict. git fetch origin <default>must succeed. Never degrade to a stale base for a verdict.- The fetched
origin/<default>tip must be an ancestor of the branch tip. If the branch is behind, stop: rebase ontoorigin/<default>and re-enter step 0. - Run the script with
HEAD_SHA= the local branch tip andBASE_SHA= the fetchedorigin/<default>tip — never a pre-computed merge-base, and never a hand-rolled two-dot diff.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 13d ago Changed · +5 lines · +4 tokens per session 7c1bcf7f3cd1
- 20d ago Changed · -1 lines 90d05fdf4515
- 23d ago Changed · -113 lines 4f2f04a5f953
- 24d ago Changed · -1 lines 8ba9c7d41cc9
- 25d ago Changed 62656d0b44dd
- 27d ago Changed · -13 lines · -169 tokens per session 7deba7d8697e
- 1mo ago Changed · -1 lines 7f4d0555abe0
- 1mo ago Changed 4e52e05cd0d8
- 1mo ago Changed · +2 lines ebc3ce294a99
- 1mo ago First seen · 398 lines · 207 tokens per session scan A 4c411183b40d
version-bump is a skill published in the GitHub repository bostonaholic/team (11 stars, last pushed 11d ago), licensed MIT. It adds 42 tokens to every session and 3,487 once invoked, about $0.0002 per session on Opus 5.5. 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
git-integration
Git commit patterns, formats, and conventions for GSD methodology. Provides atomic commits per task, structured commit messages, planning file commits, branch management, and milestone tag operations.
finishing-a-development-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work.
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm.
agent-release-manager
Agent skill for release-manager - invoke with $agent-release-manager.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.