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 dnlbox/ai-protocol --skill sync-protocolgit clone --depth 1 https://github.com/dnlbox/ai-protocolWrote 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/dnlbox/ai-protocol/sync-protocol)<a href="https://agentmods.dev/skills/dnlbox/ai-protocol/sync-protocol"><img src="https://agentmods.dev/badge/skills/dnlbox/ai-protocol/sync-protocol/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/dnlbox/ai-protocol/sync-protocol"><img src="https://agentmods.dev/badge/skills/dnlbox/ai-protocol/sync-protocol.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00015 | $0.00367 |
| Opus 5.5 | $0.00006 | $0.00147 |
| Sonnet 5.5 | $0.00003 | $0.00073 |
| Haiku 4.5 | $0.00002 | $0.00037 |
Grade A, and why
sync-protocol 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.
What it actually says
Sync protocol
Use this skill when the user requests protocol synchronisation.
Use this skill when implementation materially changes a stable repository contract.
Do not invoke this skill after ordinary feature work.
Scope
- Read accepted product intent relevant to the contract change.
- Read the current Project Specifics.
- Read the implementation evidence for the contract change.
- Edit only the Project Specifics region of
AGENTS.md. - Edit an existing
EXPERIENCE.mdonly when interaction policy changed. - Edit an existing
DESIGN.mdonly when presentation policy changed. - Preserve compatible human additions.
- Preserve unrelated project rules.
Reconciliation
- Make stable instructions match verified implementation reality.
- Keep commands exact.
- Keep validation gates executable.
- Keep architecture boundaries current.
- Keep security boundaries current.
- Keep external-operation gates current.
- Keep interaction policy current when applicable.
- Keep presentation policy current when applicable.
- Remove superseded stable instructions.
- Avoid copying current task status into stable instructions.
- Avoid copying execution history into stable instructions.
- Surface contradictions that require a product decision.
Boundaries
- Avoid editing
BUILD_STATE.md. - Avoid editing
GOVERNANCE.md. - Avoid editing
ROADMAP.md. - Avoid creating
EXPERIENCE.md. - Avoid creating
DESIGN.md. - Avoid inventing execution strategy.
- Avoid broadening the approved objective.
- Use
plan-implementationwhen execution strategy must change materially. - Use
shape-conceptwhen accepted product intent must change.
Delivery
- Apply the reconciliation within the approved objective.
- Report every changed stable instruction.
- Report every unresolved contradiction.
- Continue the approved implementation objective after reconciliation.
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 · 58 lines · 15 tokens per session scan A 279a6ce80867
sync-protocol is a skill published in the GitHub repository dnlbox/ai-protocol (19 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 367 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
shipping-a-pr
Use when finished work needs to ship as a pull request, or when creating, syncing, updating metadata, checking status, monitoring CI, or addressing review comments on a PR. Not for reviewing a PR you are not shipping.
git-workflow
Use when naming or scoping a branch, writing or fixing a commit message, picking the gitmoji for a commit, untangling history (rebase versus merge versus squash), or cutting a versioned release — the portable git-convention layer for any repo. Covers gitmoji + Conventional Commits, SemVer tags, branch hygiene…
release-notes
Write release notes for a tagged release — a business-impact summary of what changed for the user, plus a thanks section naming every contributor whose commits are in the release. Short by construction.
review-this-branch
Run the nohuman review gate (fresh-session adversarial reviewer + tamper guard) over the current branch or a GitHub pull request, with no server, no database, and no onboarding, and relay the pass/fail checklist.
worktree-pr
Decide whether a task deserves its own git worktree and, if chosen, run it end to end: branch from the integration branch rather than the current tree, keep the main working copy untouched while the task runs, compare the result against the untouched baseline before declaring it done, and prepare it for a pull request…
cut-release
Cut a new agnostic-ai release end to end. Use when the user wants to ship a new version (tag + GitHub Release).