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 seed-forge/harness-ai-kit --skill infra-woodpecker-pipeline-opsgit clone --depth 1 https://github.com/seed-forge/harness-ai-kitWrote 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/seed-forge/harness-ai-kit/infra-woodpecker-pipeline-ops)<a href="https://agentmods.dev/skills/seed-forge/harness-ai-kit/infra-woodpecker-pipeline-ops"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/infra-woodpecker-pipeline-ops/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/seed-forge/harness-ai-kit/infra-woodpecker-pipeline-ops"><img src="https://agentmods.dev/badge/skills/seed-forge/harness-ai-kit/infra-woodpecker-pipeline-ops.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Rogue Agent · line 28 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00028 | $0.00407 |
| Opus 5 | $0.00014 | $0.00204 |
| Sonnet 5 | $0.00006 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
Grade A, and why
infra-woodpecker-pipeline-ops 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 12d 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
Woodpecker Pipeline Operations
Purpose
Use this Skill to inspect Woodpecker repositories and builds, design a portable CI pipeline, or diagnose build failures. It does not assume a specific Git host, container registry, image repository, internal platform or deployment topology.
Required Configuration
Configure the companion CLI in ~/.harness-ai-kit/config.yaml:
assets:
woodpeckerctl:
woodpecker_url: https://ci.example.com/
woodpecker_token: <store-outside-source-control>
The checked-in config.defaults.yaml is the configuration contract. Use
command-line values for a one-off action and environment variables only as CI
fallbacks. Do not create a separate ~/.woodpeckerctl source of truth.
Workflow
- Identify repository purpose before changing a pipeline: build-only images, libraries and deployed applications have different delivery boundaries.
- Use
woodpeckerctl doctor, repository inspection and build logs before modifying configuration. - Keep platform credentials in Woodpecker secrets and use secret references in pipeline definitions; never write registry credentials or tokens into a repository.
- Keep build integration separate from deployment configuration. Enable a deployment only when its target, approval path and rollback are explicit.
- Trigger or observe a build, inspect logs and report the resulting artifact coordinates without exposing secret values.
Guardrails
- Treat repository activation, secret management and trusted-build changes as operator-controlled actions.
- Build and log queries are read-only. Writes must respect the configured role and the target platform's access controls.
- Use public placeholders in examples. Private registry addresses, hostnames, user names, repository names and release evidence never enter the public projection.
What ships with it
5 files 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.
- 12d ago First seen · 53 lines · 28 tokens per session scan A 216c8f0db0b7
infra-woodpecker-pipeline-ops is a skill published in the GitHub repository seed-forge/harness-ai-kit (22 stars, last pushed 12d ago), licensed Apache-2.0. It adds 28 tokens to every session and 407 once invoked, about $0.0001 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
Prompt Version Control Workflow
Sets up a prompt versioning system with naming conventions, diff tracking, A/B evaluation gates before promotion, and rollback triggers.
production-release-gating
Stop every push/merge to main from shipping to production — deploy only on a real release. Use when a merge to main unexpectedly deploys to prod, when you want production to deploy only on a semantic-release version (not every commit), when setting up preview-on-feature-branch but gated-prod-on-main, wiring a Vercel…
vercel-preview-cleanup
Install a GitHub Actions workflow that deletes a branch's Vercel PREVIEW deployments when that branch is deleted — every deployment it accumulated, not just the aliased URL (Vercel keeps one immutable deployment per push, so a 15-push branch leaves 15 live URLs). Requires Vercel; if you just want stale git branches…
code-complexity-stats-pr
Add a GitHub Actions workflow that posts code-size and cost statistics — lines of code, per-language breakdown, complexity, and a COCOMO "what would this cost to build" estimate — as a sticky comment on every pull request, using scc. Use when you want a per-PR code-stats or "worth of the codebase" comment, to show LOC…
bazel-build-optimization
Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.