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 skills add navikt/copilot --skill conventional-commitgit clone --depth 1 https://github.com/navikt/copilotWrote 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/navikt/copilot/conventional-commit)<a href="https://agentmods.dev/skills/navikt/copilot/conventional-commit"><img src="https://agentmods.dev/badge/skills/navikt/copilot/conventional-commit/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/navikt/copilot/conventional-commit"><img src="https://agentmods.dev/badge/skills/navikt/copilot/conventional-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Anti-Refusal · line 80 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00022 | $0.00700 |
| Opus 5.5 | $0.00009 | $0.00280 |
| Sonnet 5.5 | $0.00004 | $0.00140 |
| Haiku 4.5 | $0.00002 | $0.00070 |
Grade A, and why
conventional-commit 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 1mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conventional Commit Skill
Generate commit messages following the Conventional Commits specification, adapted for Nav projects.
Format
<type>(<scope>): <description>
[optional body]
[optional footer]
Types
| Type | Usage |
|---|---|
feat |
New functionality |
fix |
Bug fix |
docs |
Documentation-only changes |
style |
Formatting, semicolons, etc. (no code change) |
refactor |
Code that neither fixes a bug nor adds a feature |
perf |
Performance changes |
test |
Adding or fixing tests |
build |
Build system or dependency changes |
ci |
CI configuration changes |
chore |
Other changes that don't affect code |
Nav-relevant scopes
feat(vedtak): add support for complaint decisions
fix(auth): fix token validation for TokenX
docs(api): update OpenAPI spec for the vedtak endpoint
refactor(repository): use CTE for better readability
test(controller): add integration test with MockOAuth2Server
build(deps): upgrade Spring Boot to 3.4.1
ci(deploy): add prod deploy step
perf(db): add index on bruker_id
chore(nais): update resource limits
Breaking Changes
feat(api)!: change response format for the vedtak endpoint
BREAKING CHANGE: The `vedtakDato` field has been changed to `opprettetDato`.
Consumers must update their parsing.
Rules
- First line: max 72 characters
- Use imperative form: "add", not "added" or "adds"
- Don't end with a period
- Use Norwegian or English consistently within the project
- Reference Jira/GitHub issue in footer:
Closes #123orRefs NAV-1234
Examples
# Simple feature
git commit -m "feat(søknad): add validation of national identity number"
# Bugfix with reference
git commit -m "fix(auth): handle expired refresh token
The refresh token was not renewed upon expiration, which caused
users to be logged out without warning.
Fixes #456"
# Dependency update
git commit -m "build(deps): upgrade postgresql driver to 42.7.4"
# Breaking change
git commit -m "feat(api)!: remove deprecated /api/v1/vedtak endpoint
BREAKING CHANGE: /api/v1/vedtak has been removed. Use /api/v2/vedtak."
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.
- 1mo ago First seen · 108 lines · 22 tokens per session scan A 3ee8419b48ef
conventional-commit is a skill published in the GitHub repository navikt/copilot (55 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 700 once invoked, about $0.0001 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
loom-git-workflow
Git operations guidance including branching strategies, commit conventions, merge workflows, conflict resolution, and worktree management.
configure-git-repository
Configure a Git repository with proper .gitignore, branch strategy, commit conventions, hooks, and remote setup. Covers initial setup and common patterns for R, Node.js, and Python projects. Use when initializing version control for a new project, adding a .gitignore for a specific language or framework, setting up…
commit-changes
Stage, commit, and amend changes with conventional commit messages. Covers reviewing changes, selective staging, writing descriptive commit messages using HEREDOC format, and verifying commit history. Use when saving a logical unit of work to version control, creating a commit with a conventional message, amending the…
squash-branch
Review commits in a branch, date range, or recent history; group related work into a clean linear history; and verify that the final tree is unchanged. Use when the user asks to squash commits, clean Git history, combine WIP commits, organize today's commits, or prepare a readable commit stack.
spec-apply
Implement an OpenSpec change's tasks in parallel - read the task queue, plan file-disjoint waves, dispatch one agent per task into its own worktree, verify, tick the checkbox, commit, repeat. Use when the user says "apply the change", "implement the change", "run the tasks", "work the tasks in parallel", "fan out the…
spec-propose
Draft the OpenSpec change artifacts - proposal.md, the specs/ delta, design.md, tasks.md - on a fresh branch, install the wave rules that make tasks.md parallel-safe, validate, and commit. Use when the user says "propose this", "write the proposal", "spec this out", "/spec-propose", "turn this into an OpenSpec…