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 AcKeskin/contexture --skill close-outgit clone --depth 1 https://github.com/AcKeskin/contextureWrote 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/ackeskin/contexture/close-out)<a href="https://agentmods.dev/skills/ackeskin/contexture/close-out"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/close-out/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/ackeskin/contexture/close-out"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/close-out.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00089 | $0.03460 |
| Opus 5.5 | $0.00036 | $0.01384 |
| Sonnet 5.5 | $0.00018 | $0.00692 |
| Haiku 4.5 | $0.00009 | $0.00346 |
Grade A, and why
close-out 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
close-out
The scope chain's terminus. The forward chain (envision → spec → draft-plan → blueprint → execute) authors versioned artefacts up to running the plan; it has no close. /close-out <slug> is that close — it runs after /execute confirms done-criteria met and does three things, in order:
- Reconcile — make the slug's canonical spec say how it behaves now, not what we planned, preserving the original intent via the version chain.
- Retire — move the spent working artefacts (plan, blueprint, superseded spec versions) to a dated archive folder. The reconciled spec stays live; the working set becomes audit history.
- Record — emit one ship line to the canonical
CHANGELOG.md(viaupdate-changelog), not a hand-copy into three ledgers.
It collapses the "what's true now / what shipped" scatter across spec / ledgers / git into one reconcile-and-record act — leverage, not ceremony.
Where it sits. The spec's done-criteria open the boundary ("what done means"); /close-out closes it ("done, here's the now-current spec, the working artefacts are retired"). /checkpoint --scope corpus detects intent-vs-shipped drift after the fact; /close-out acts to close that drift at ship time — they compose: checkpoint catches what drifted post-ship or what close-out missed.
When to run
- User types
/close-out <slug>(explicit trigger; slug required). - User says "close out
<slug>", "reconcile what shipped for<slug>", "wrap up the<slug>work", "retire the<slug>plan now it's shipped". - The execute-side invitation:
/executeoffers/close-outwhen a plan completes with all done-criteria met (execute is the doorway; the user invokes; this skill does the work). The offer is never an auto-run. - Otherwise never auto-fires. Mode A. It moves files and edits the canonical spec — both reversible-with-effort but not cheap to undo — so every write passes a propose-confirm gate (§ below). No hook, no session-end trigger.
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.
- 1mo ago First seen · 132 lines · 89 tokens per session scan A a1031de1e0ae
close-out is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 2mo ago), licensed MIT. It adds 89 tokens to every session and 3,460 once invoked, about $0.0004 per session on Opus 5.5. 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
benchmark
Where the queue command exists, run every benchmark, profiler run, load test or other timing measurement as queue bench -- followed by the command in the background, never directly. Run builds and tests through dotnet, cargo, bun and uv in the background too, one at a time, because each waits for a free build slot…
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
adk-verify-snippets
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…
adk-setup
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…
architecture-patterns
Architecture validation and patterns for clean architecture, backend structure enforcement, project structure validation, test standards, and context-aware sizing. Use when designing system boundaries, enforcing layered architecture, validating project structure, defining test standards, or choosing the right…
testing-llm
LLM and AI testing patterns — mock responses, evaluation with DeepEval/RAGAS, structured output validation, and agentic test patterns (generator, healer, planner). Use when testing AI features, validating LLM outputs, or building evaluation pipelines.