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 skills/yaalalabs/agent-kernel/ak-dev-sync-skills-and-docs-from-commitnpx skills add yaalalabs/agent-kernel --skill ak-dev-sync-skills-and-docs-from-commitgit clone --depth 1 https://github.com/yaalalabs/agent-kernelWrote 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/yaalalabs/agent-kernel/ak-dev-sync-skills-and-docs-from-commit)<a href="https://agentmods.dev/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-and-docs-from-commit"><img src="https://agentmods.dev/badge/skills/yaalalabs/agent-kernel/ak-dev-sync-skills-and-docs-from-commit.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 | $0.00061 | $0.02134 |
| Opus 5 | $0.00030 | $0.01067 |
| Sonnet 5 | $0.00012 | $0.00427 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
ak-dev-sync-skills-and-docs-from-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 4d 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.
Sync Skills and Docs From Commit Hash
Use this skill to process a specific commit hash and synchronize both skill trees and documentation based on what changed in that commit.
This skill combines the intent of:
ak-dev-sync-skills-from-branchak-dev-sync-docs-from-branch
but uses a commit hash as the primary unit of analysis.
Goal
Given a commit hash (typically on develop after PR merge), analyze the introduced code changes and update:
- developer skills under
.agents/skills/ - user skills under
ak-py/src/agentkernel/skills/ - documentation surfaces including root docs, package docs, docs website, deployment READMEs, and example READMEs
Primary Automation Context
This skill is intended for GitHub Actions automation when a commit lands on develop from a merged PR.
Expected automation behavior:
- Trigger on push to
develop. - Ignore direct commits and ignore bot/app-driven commits.
- Resolve PR metadata associated with the pushed commit hash.
- Run this skill against that commit hash.
- Commit generated skill/docs updates to an automation branch.
- Open a PR for human review.
- Human approves and merges.
- Future runs ignore automation-generated sync PR commits to prevent circular updates.
Inputs
Required:
commit_sha: full SHA of the commit to analyze
Optional but recommended:
base_branch: defaultdeveloprepo_ownerrepo_nameassociated_pr_number
Step 1: Validate Commit Eligibility
Before analyzing, validate that this commit should be processed.
Skip processing when any of the following is true:
- Commit is not on
develop. - Commit is from a bot/app actor (for example
github-actions[bot]or any*[bot]). - Commit is not associated with a merged PR into
develop(direct push or manual commit). - Commit belongs to an automation-generated sync PR (loop prevention).
- Example loop markers:
- PR label:
auto-skill-doc-sync - automation branch prefix:
auto/skill-doc-sync/ - title prefix:
chore(auto): sync skills/docs
- PR label:
- Example loop markers:
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.
- 4d ago First seen · 276 lines · 61 tokens per session scan A ad499af83a05
ak-dev-sync-skills-and-docs-from-commit is a skill published in the GitHub repository yaalalabs/agent-kernel (166 stars, last pushed today), licensed Apache-2.0. It adds 61 tokens to every session and 2,134 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
notion
Notion workspace integration for searching pages, managing databases, creating postmortems, and exporting RCA findings.
datadog
Datadog monitoring integration for querying logs, metrics, monitors, events, traces, hosts, and incidents during RCA investigations.
scaleway
Scaleway cloud integration for managing instances, Kapsule Kubernetes clusters, object storage, and managed databases via CLI and Terraform.
bitbucket
Bitbucket code repository integration for managing repos, branches, PRs, issues, and CI/CD pipelines.
cloudbees
CloudBees CI integration for investigating builds, deployments, pipeline stages, and test results during RCA.
cloudflare
Cloudflare integration for DNS, CDN, WAF, edge diagnostics, and remediation with zone management, analytics, security events, and cache control.