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 marcusgoll/Spec-Flow --skill production-deployment-phasegit clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote 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/marcusgoll/spec-flow/production-deployment-phase)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/production-deployment-phase"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/production-deployment-phase.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 5.1 | $0.00052 | $0.02913 |
| Opus 5 | $0.00026 | $0.01456 |
| Sonnet 5 | $0.00010 | $0.00583 |
| Haiku 4.5 | $0.00005 | $0.00291 |
Grade A, and why
production-deployment-phase scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://production.example.com$ENDPOINT") How it starts
The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start> <production_deployment_workflow> Prerequisite-driven production promotion:
- Verify staging validation: Check state.yaml manual_gates.staging_validation.status = approved
- Bump semantic version: Update package.json/version files (major.minor.patch)
- Create release tag: Tag git commit with new version
- Deploy to production: Push to production branch or trigger deployment
- Run health checks: Verify endpoints, databases, services operational
- Generate ship report: Document deployment artifacts and metadata
- Monitor post-deploy: Watch logs, metrics, alerts for 15-30 minutes
Example workflow:
Verifying staging validation complete... ✅
Current version: 2.6.0
Bump type: minor (new features added)
New version: 2.7.0
Creating git tag v2.7.0... ✅
Pushing to production branch... ✅
Triggering production deployment... ✅
Health checks:
API endpoints: 200 OK ✅
Database connections: healthy ✅
Cache: operational ✅
CDN: propagated ✅
Production deployment successful!
Release: https://github.com/user/repo/releases/tag/v2.7.0
Ship report: specs/NNN-slug/production-ship-report.md
</production_deployment_workflow>
<trigger_conditions> Auto-invoke when:
/ship-prodcommand executed- User mentions "deploy to production", "ship to prod", "production release"
- state.yaml shows current_phase: ship-prod
Prerequisites required:
- Staging validation approved (manual_gates.staging_validation.status = approved)
- Rollback gate passed (quality_gates.rollback.status = passed)
- Git repository has remote configured
- Production deployment configuration exists </trigger_conditions> </quick_start>
Check workflow state for staging validation approval:
# Read workflow state
STATE_FILE="specs/$(ls -t specs/ | head -1)/state.yaml"
STAGING_STATUS=$(grep -A2 "staging_validation:" "$STATE_FILE" | grep "status:" | awk '{print $2}')
if [ "$STAGING_STATUS" != "approved" ]; then
echo "❌ BLOCKED: Staging validation not approved"
echo "Current status: $STAGING_STATUS"
echo "Run: /validate-staging to complete manual validation"
exit 1
fi
echo "✅ Staging validation approved"
Blocking conditions:
- Staging validation status ≠ approved
- Rollback gate status ≠ passed
- No staging deployment exists </step_1_verify_staging>
<step_2_bump_version> 2. Bump Semantic Version
Determine version bump type and update version files:
# Read current version
CURRENT_VERSION=$(node -p "require('./package.json').version")
# Determine bump type from CHANGELOG or git commits
# - major: Breaking changes
# - minor: New features (backward compatible)
# - patch: Bug fixes only
# Use npm version or manual update
npm version minor -m "chore: bump version to %s for production release"
NEW_VERSION=$(node -p "require('./package.json').version")
echo "Version bumped: $CURRENT_VERSION → $NEW_VERSION"
Semantic versioning rules:
- Major (X.0.0): Breaking changes, API contract changes
- Minor (0.X.0): New features, backward compatible
- Patch (0.0.X): Bug fixes, no new features
Files to update:
- package.json (version field)
- CHANGELOG.md (unreleased → version section)
- Any version constants in code </step_2_bump_version>
<step_3_create_release_tag> 3. Create Git Release Tag
Tag the commit and push to remote:
# Create annotated tag
git tag -a "v${NEW_VERSION}" -m "Release v${NEW_VERSION}
$(sed -n "/## \[${NEW_VERSION}\]/,/## \[/p" CHANGELOG.md | head -n -1)"
# Push tag to remote
git push origin "v${NEW_VERSION}"
echo "✅ Tag created and pushed: v${NEW_VERSION}"
Tag format:
- Annotated tags required (not lightweight)
- Prefix with "v" (e.g., v2.7.0)
- Include CHANGELOG excerpt in tag message </step_3_create_release_tag>
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 · 423 lines · 52 tokens per session scan A b6cd507339c1
production-deployment-phase is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 52 tokens to every session and 2,913 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 2026-09-03.
Other skills, from other repositories
skill-release-engineering
Prepara releases seguros com changelog, migrações, smoke tests, rollback, feature flags, CI e checklist operacional.
changelog-guide
A guide for maintaining a CHANGELOG.md file, which records notable changes made in each software release. It follows the Keep a Changelog format and groups changes such as additions, updates, and fixes.
release-standards
A guide for preparing software releases with semantic versioning and changelogs. Semantic versioning uses major, minor, and patch numbers to describe the kind of change in a release.
godot-devtool-release-verify
Use when changing or releasing the godot-devtool MCP package itself, including tool catalog, build output, Godot addon, docs, and local Skill sync.
release
Cuts a project release. Discovers the project's release procedure (Makefile target, RELEASING.md, CI workflow, etc.) and offers to capture it durably if missing. Always invokes /review-release as preflight, proposes a version bump from CHANGELOG, then presents an exact command plan for operator confirmation before…
review-release
Pre-release readiness review. Scans for debug artifacts, version mismatches, changelog gaps, git hygiene issues, breaking changes, and license compliance. Runs tests and build verification. Presents consolidated findings for human review before release.