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 finalize-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/finalize-phase)<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/finalize-phase"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/finalize-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 | $0.00065 | $0.04531 |
| Opus 5 | $0.00032 | $0.02266 |
| Sonnet 5 | $0.00013 | $0.00906 |
| Haiku 4.5 | $0.00006 | $0.00453 |
Grade A, and why
finalize-phase 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 — 670 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill orchestrates the /finalize phase, the final step after successful deployment to production, direct-prod, or local build.
For Epic Workflows (v5.0+):
- Generate comprehensive walkthrough.md with velocity metrics, sprint results, lessons learned
- Run post-mortem audit with pattern detection (after 2-3 epics)
- Offer workflow healing with improvement recommendations
- Detect patterns for custom skills/commands generation
For Feature Workflows:
- Standard finalization (roadmap, artifacts, docs, branches)
Inputs: Deployed feature/epic, phase artifacts, ship report, state.yaml Outputs: walkthrough.md (epics only), updated roadmap, archived artifacts, updated documentation Expected duration: 10-15 minutes (features), 20-30 minutes (epics with walkthrough)
<quick_start> After deployment completes, finalize the workflow:
Epic Workflows (NEW in v5.0): 0. Generate walkthrough - Comprehensive epic summary with velocity metrics, sprint results, lessons learned, pattern detection
- Run post-mortem audit - Final effectiveness analysis with improvement recommendations
- Offer workflow healing - Apply discovered improvements with user approval
All Workflows (features + epics):
- Update roadmap - Move to "Shipped" with completion date, version, production URL
- Archive artifacts - Verify all phase artifacts in specs/NNN-slug/ or epics/NNN-slug/
- Update documentation - README, CHANGELOG, user guides (if applicable)
- Clean up branches - Delete feature branch locally and remotely
- Commit finalization - Small commit documenting workflow closure
Key principles:
- Clean closure preserves knowledge and enables learning
- Epic walkthroughs enable self-improving workflow system
- Pattern detection (after 2-3 epics) suggests custom automation </quick_start>
If deployment incomplete, return to /ship phase.
Detect epic vs feature workflow and generate comprehensive walkthrough for epics.
Detection:
if [ -f "epics/*/epic-spec.xml" ]; then
WORKSPACE_TYPE="epic"
EPIC_DIR=$(dirname "epics/*/epic-spec.xml")
else
WORKSPACE_TYPE="feature"
# Skip to Step 1 (standard finalization)
continue
fi
If feature workflow: Skip this step entirely, proceed to Step 1
If epic workflow: Generate walkthrough before standard finalization
Walkthrough Generation Pipeline:
-
Gather all epic artifacts:
- epic-spec.xml (epic specification)
- research.xml (research phase output)
- plan.xml (plan phase output with meta-prompting)
- sprint-plan.xml (task breakdown with dependency graph)
- state.yaml (state tracking across phases)
- audit-report.xml (workflow effectiveness analysis)
- preview-report.xml (manual testing decision)
- Sprint results from epics/NNN-slug/sprints/*/
-
Calculate velocity metrics:
- Expected parallelization multiplier (from sprint-plan.xml)
- Actual parallelization multiplier (from audit-report.xml)
- Time saved in hours (parallel vs sequential execution)
- Duration from start to completion
-
Extract key information:
- Epic goal and success metrics
- Phases completed with timestamps
- Sprint execution results (status, tasks, duration, contracts, tests)
- Validation results (optimization, preview decision)
- Key files modified
- Next steps (enhancements, technical debt, monitoring needs)
What ships with it
2 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.
- 4d ago First seen · 670 lines · 65 tokens per session scan A 158c2fd30324
finalize-phase is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 4,531 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 2026-09-03.
Other skills, from other repositories
create-github-issue
Create GitHub issues using GitHub CLI with support for templates, labels, assignees, milestones, and draft issues. Use when the user asks to create a GitHub issue, file a bug report, submit a feature request, or open an issue in a GitHub repository.
machinist
Use Machinist to create, assign, monitor, and resume software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, lifecycle labels, direct runs, or managed queue.
team-release
Orchestrate the release team: coordinates release-manager, qa-lead, devops-engineer, and producer to execute a release from candidate to deployment.
linear-cli
Use when the user wants to list, view, start, create, or update Linear issues from the terminal via schpet/linear-cli, including setup, auth, repo config, and safe read/write boundaries.
magpie-setup-override-upstream
Walk an adopter through promoting a local .apache-magpie-overrides/ .md file into a PR against apache/magpie. After the PR merges and the adopter runs /magpie-setup upgrade, the override file is no longer needed and the skill prompts for its removal.
magpie-setup-shared-config-sync
Commit + push the user's shared Claude config to the /.claude-config private dotfile-style sync repo. Inspects for uncommitted local edits and unpushed commits, drafts a commit message, and after explicit approval commits and pushes. Runs git pull --rebase first if the local checkout is behind, so a push never…