web-ci-spec

web-ci-spec is a skill for Claude Code from howar31/magi-workflow. It costs 52 tokens per session (1,781 once invoked), scanned A, original, MIT.

A planning guide for documenting a sprint's continuous integration and delivery pipeline, the automated process that tests, builds, and releases code.

In plain words
What is it for?
Use it to draft CI.md for systems such as GitHub Actions, Cloud Build, or GitLab CI. It plans the work but does not modify workflows, deploy, or rotate secrets.
Why use it?
It makes pipeline stages, secret handling, deployment, and rollback decisions explicit before changes are made.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the magi plugin — 15 skills, 2 agents shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add howar31/magi-workflow
Claude Code
/plugin install magi

Made for: Claude Code.

Or install magi, the plugin that ships this one along with the rest of its 15 skills, 2 agents.

Wrote 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.

agentmods badge for web-ci-spec

README.md
[![agentmods](https://agentmods.dev/badge/skills/howar31/magi-workflow/web-ci-spec.svg)](https://agentmods.dev/skills/howar31/magi-workflow/web-ci-spec)
Your own site
<a href="https://agentmods.dev/skills/howar31/magi-workflow/web-ci-spec"><img src="https://agentmods.dev/badge/skills/howar31/magi-workflow/web-ci-spec.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,781 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00052 $0.01781
Opus 5 $0.00026 $0.00890
Sonnet 5 $0.00010 $0.00356
Haiku 4.5 $0.00005 $0.00178

Measured 6d ago against content hash 81343a33da31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

web-ci-spec scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Required for any shared-env deploy. Use the curl + jq pattern from the
skills/web-ci-spec/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/magi:web-ci-spec — CI/CD elaboration

You are the coordinator. Plan a CI/CD pipeline change and capture the analysis in magi/<num>-<slug>/CI.md. You never push to the workflow, trigger a deploy, or rotate a secret. Read references/domain/web/ci-cd.md before starting.

0. Preflight

PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-}"
[[ -z "$PLUGIN_ROOT" ]] && PLUGIN_ROOT="$(cd "$(dirname "$BASH_SOURCE[0]")/../.." 2>/dev/null && pwd)"
USER_CONFIG="$HOME/.config/magi-workflow/config.json"

If config missing → tell user to run /magi:setup.

0.5. State preflight (auto-refuse if not allowed)

STATE_JSON=$(bash "$PLUGIN_ROOT/scripts/shared/detect-state.sh")
blocked=$(jq -r '.disallowed_skills["web-ci-spec"] // empty' <<<"$STATE_JSON")
if [[ -n "$blocked" ]]; then
  reason=$(jq -r '.disallowed_skills["web-ci-spec"].reason' <<<"$STATE_JSON")
  suggest=$(jq -r '.disallowed_skills["web-ci-spec"].suggest' <<<"$STATE_JSON")
  echo "Cannot run /magi:web-ci-spec: $reason"
  echo "Suggested: $suggest"
  exit 1
fi

--force skips preflight (advanced/recovery only).

1. Locate sprint + CI tool

Find the sprint folder (default: most recent; or --sprint <num>-<slug>).

Detect the CI tool per references/domain/web/ci-cd.md "Discovery":

  • .github/workflows/*.yml → GitHub Actions
  • cloudbuild.yaml / cloudbuild/*.yaml → Cloud Build
  • .gitlab-ci.yml → GitLab CI
  • azure-pipelines.yml → Azure DevOps
  • Jenkinsfile → Jenkins
  • vercel.json → Vercel
  • wrangler.toml → Cloudflare

If multiple coexist (e.g. GHA for tests + Cloud Build for prod deploy), document the boundary explicitly.

2. Read existing pipeline + spec

  • List existing workflow files; for each, summarise: trigger, stages, duration, last failure rate (if available via gh run list or gcloud builds list).
  • Read PLAN/SPEC.md to understand what change is needed:
    • New tests added → wire them into test stage?
    • New deployable surface → new deploy job?
    • New secret needed → secret store + scoping plan?
    • Performance budget regression → add budget check?

Read the full file on GitHub · 207 lines

Changes

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.

  1. 6d ago First seen · 207 lines · 52 tokens per session scan A 81343a33da31

Subscribe to this mod's changes

web-ci-spec is a skill published in the GitHub repository howar31/magi-workflow (2 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 1,781 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

pipeline-digest

Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is green, and which branches went stale, and notifies the operator only when that state actually moved since the last run. Use when the operator asks "what moved in the pipeline", "anything to ship"…

gtapps/claude-code-hermit · 99 tokens

platform-operations

Unified platform operations guidance for CI/CD pipeline design, deployment strategies, observability, SLI/SLOs, and incident-ready rollouts. Use when building release workflows, production monitoring, or reliability controls.

rsmdt/the-startup · 45 tokens

ccc-broadcast

Relay CC Commander build, deploy, CI, task, and cost signals to your team's chat or email so non-devs see what shipped — read-only, no secrets in payloads.

KevinZai/commander · 41 tokens

ccc-ci

CI/CD webhook channel. Receive GitHub Actions, Vercel, Railway deploy events in your session. Auto-triggers $ccc-doctor on failures.

KevinZai/commander · 34 tokens

watch-patterns

Correct construction of watchers for long-running operations. TRIGGER when: arming observation of a long-running operation (CI run, deploy, transfer, GC/prune, log stream), writing poll/until loops, or using the Monitor tool. SKIP: defining production alerts/metrics (use monitoring-observability); log formatting (use…

komluk/scaffolding · 76 tokens

loop-on-ci

Monitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.

Kripu77/software-factory · 28 tokens