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 agentmods add skills/acendas/shipyard/evaluating-sprint-completenpx skills add Acendas/shipyard --skill evaluating-sprint-completegit clone --depth 1 https://github.com/Acendas/shipyardWrote 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/acendas/shipyard/evaluating-sprint-complete)<a href="https://agentmods.dev/skills/acendas/shipyard/evaluating-sprint-complete"><img src="https://agentmods.dev/badge/skills/acendas/shipyard/evaluating-sprint-complete.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 | $0.00017 | $0.01770 |
| Opus 5 | $0.00009 | $0.00885 |
| Sonnet 5 | $0.00003 | $0.00354 |
| Haiku 4.5 | $0.00002 | $0.00177 |
Grade A, and why
evaluating-sprint-complete 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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluating Sprint Complete
A sprint is complete only when eight invariants hold simultaneously. This skill is the gate /ship-execute runs after the last wave-completion verifier passes and before declaring the sprint shippable. It composes the wave-level guarantees into the sprint-level guarantee.
When to Invoke
/ship-execute Step 5 (Sprint Completion) calls this skill in the pre-review mode after:
- The full-suite test command exits 0.
- The sprint-boundary verify-probe has completed and its capture is on disk.
- The execute pipeline has completed all wave gates and is ready to hand the sprint to review.
Other entry points:
/ship-reviewmay invoke this skill withreview_verdict_pathafter its scanner/review stages as a post-review release pre-flight.- Manual invocation when a user wants to spot-check sprint completeness before declaring shippable.
Inputs
sprint_id— e.g.,sprint-003data_dir— literal<SHIPYARD_DATA>pathworking_branch— git branchsprint_base_sha— working-branch HEAD when the sprint started (from SPRINT.md frontmatterbase_shaor computed viagit merge-base)sprint_head_sha— current HEADsprint_verify_capture— path to the sprint-boundary verify-probe capturesprint_verify_exit_code— exit code from sprint-boundary verifydemo_probe_event_window_start— ISO timestamp; onlyacceptance_probe_completed/user_flow_probe_confirmedevents at or after this count for Invariant 8 (typically SPRINT.mdstarted_at)review_verdict_path— path to the latest/ship-reviewverdict file (or null if review hasn't run)
The Eight Invariants — Summary Table
Detailed per-invariant logic and primitives live in references/invariants.md. Read that when implementing the skill; the summary below is for orientation.
| # | Invariant | Primitive |
|---|---|---|
| 1 | Every completed task has integration evidence; returned commits remain reachable via working branch or shipyard/keep-* anchors |
shipyard-data verify-wave-integrated + shipyard-context scan-events --tail 1000 task_dispatch_returned |
| 2 | Sprint-boundary verify-probe exits 0 with non-empty capture | Read sprint_verify_capture + exit code param |
| 3 | Every linked spec item is in the expected lifecycle state for this invocation (in-progress during pre-review execute; done/released post-review) |
Read feature frontmatter |
| 4 | Spec coverage shows no orphan AC for this sprint's slice | Search diff + linked-task probes for AC mapping |
| 5 | No silent-failure / loop-detected / bogus-pass / anti-stub / wave-escalated markers in window | shipyard-context scan-events --tail 2000 silent_failure loop_detected operational_task_bogus_pass anti_stub_finding wave_check_escalated |
| 6 | No uncommitted state in any shipyard/wt-* worktree |
shipyard-context check-dirty-worktrees |
| 7 | Code-review verdict recommends approve or issues (not changes) | Read review_verdict_path frontmatter |
| 8 | Every shipped feature's user_flow_probe was proven in the sprint window — by exit code (auto) or human confirmation (assisted/manual) |
shipyard-context scan-events --tail 2000 acceptance_probe_completed + … user_flow_probe_confirmed + feature frontmatter user_flow_probe: |
What ships with it
4 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 · 123 lines · 17 tokens per session scan A 2fca5b189c01
evaluating-sprint-complete is a skill published in the GitHub repository Acendas/shipyard (2 stars, last pushed 23d ago), licensed MIT. It adds 17 tokens to every session and 1,770 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 2026-08-31.
Other skills, from other repositories
write-epic
Produces a complete epic definition following Atlassian agile guidance. An epic captures a large initiative that is too big for a single sprint and must be decomposed into user stories.
write-user-story
Produces a complete, ready-to-groom user story following the standard Atlassian/agile format. It applies the INVEST criteria and the 3 Cs framework (Card, Conversation, Confirmation) to ensure each story is well-scoped, valuable, and testable — not just syntactically correct.
pr-review-expert
Professional Pr Review Expert skill. Orchestrate technical collaboration, design reviews, sprint planning, and system diagnostics.
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
batch-all-issues
Resolve every open issue one at a time: fact-check each with web research, close the ones that need no action, and run the goal-pr skill to fix, review, and merge the ones that do — repeating until no actionable issues remain.
moai-workflow-worktree
Git worktree management for parallel SPEC development with isolated workspaces, automatic branch registration, and seamless MoAI-ADK integration. Use when setting up parallel development environments.