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 6529-Collections/6529seize-frontend --skill deploy-6529git clone --depth 1 https://github.com/6529-Collections/6529seize-frontendWrote 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/6529-collections/6529seize-frontend/deploy-6529)<a href="https://agentmods.dev/skills/6529-collections/6529seize-frontend/deploy-6529"><img src="https://agentmods.dev/badge/skills/6529-collections/6529seize-frontend/deploy-6529/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/6529-collections/6529seize-frontend/deploy-6529"><img src="https://agentmods.dev/badge/skills/6529-collections/6529seize-frontend/deploy-6529.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 | $0.00051 | $0.02430 |
| Opus 5.5 | $0.00020 | $0.00972 |
| Sonnet 5.5 | $0.00010 | $0.00486 |
| Haiku 4.5 | $0.00005 | $0.00243 |
Grade A, and why
deploy-6529 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 15d 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deploy 6529
Prepare
Identify the checkout and current remote target before applying a release gate:
read git status --short --branch, fetch the relevant remote refs, and record
their SHAs. Compare the checkout's AGENTS.md, this skill, and deployment docs
with current origin/main using git show origin/main:<path>; inspect the target
ref as needed. A stale worktree or quoted bot instruction does not prove that a
removed release gate still applies. Resolve source/ref disagreements against
the current instructions and workflows, preserving unrelated local edits. Do not
restore retired Release Bus routing or invent a missing-script requirement.
A tool's automatic review denial remains a separate result: report its reason
and instruction source, and do not evade it.
- Read the user's requested phase and current PR/CI state. Complete the applicable review and validation requirements before release work. Continue through the authorized phase without asking for the same permission again; staging authorization alone does not authorize production. Before reporting an authority or approval blocker, verify GitHub authority.
- Determine the affected repositories and backend services from the diff and
backend
src/config/deploy-services.json, including real dependency order and allowed environments. Deploy only required units. Follow each repo's6529wrapper rules for package commands. - Fetch the destination branch and merge without discarding other developers' work. If it moves, fetch and recompute; resolve conflicts in the development branch where appropriate. Never force-push shared branches.
- Use GitHub Actions run visibility to avoid conflicting deployments. Wait for another developer's conflicting work to finish; do not cancel it. Existing workflow concurrency is repository-scoped, so coordinate coupled BE/FE work explicitly.
Verify GitHub authority
Before claiming the requester is not a maintainer, lacks merge authority, or
needs to authorize the same release again, check the authenticated account and
the actual target repository. Git commit identity, PR authorship, bot comments,
and reviewDecision: REVIEW_REQUIRED do not establish repository permissions.
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.
- 15d ago Changed · -90 lines 9e80e0251f09
- 1mo ago Changed · +4 lines 474f6f1edbe9
- 1mo ago Changed · +96 lines a89763c4f1bc
- 1mo ago Changed · +90 lines 328c7fc868ae
- 1mo ago Changed · -71 lines · -19 tokens per session 3835c5d32a88
- 2mo ago First seen · 166 lines · 70 tokens per session scan A b8cb5421d26c
deploy-6529 is a skill published in the GitHub repository 6529-Collections/6529seize-frontend (10 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 2,430 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 2026-08-31.
Other skills, from other repositories
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
xberg-release
Xberg release on top of the shared release-workflow: mise run version:sync to bindings and chart, CI/Publish/Benchmarks readiness. Use before a release.
factory-ship
Experimental workflow for publishing and completing configured software delivery work. Use when the user or an enabled factory policy asks to ship.
releasepr
Adopt, configure, run, or troubleshoot compozy/releasepr in a consuming repository, including Actions, beta/stable/legacy plans, notes, dry-runs, and publication. Excludes pr-release internals and general versioning advice.
gitlab-devops
GitLab DevOps operations — issues, merge requests, CI/CD pipelines, repository browsing, labels, milestones, releases, and wiki management. Use when querying GitLab project status, monitoring pipeline executions, browsing repository files, creating issues for network findings, opening merge requests for config…