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 bricerising/enterprise-software-playbook --skill finishgit clone --depth 1 https://github.com/bricerising/enterprise-software-playbookWrote 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/bricerising/enterprise-software-playbook/finish)<a href="https://agentmods.dev/skills/bricerising/enterprise-software-playbook/finish"><img src="https://agentmods.dev/badge/skills/bricerising/enterprise-software-playbook/finish/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/bricerising/enterprise-software-playbook/finish"><img src="https://agentmods.dev/badge/skills/bricerising/enterprise-software-playbook/finish.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 | $0.00072 | $0.01738 |
| Opus 5 | $0.00036 | $0.00869 |
| Sonnet 5 | $0.00014 | $0.00348 |
| Haiku 4.5 | $0.00007 | $0.00174 |
Grade A, and why
finish 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 9d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finish
Overview
Turn “it works on my machine” into “this is ready to ship” by running verification, checking boundary discipline, and reporting changes in a consistent format.
Chooser (What To Verify By Change Type)
- Tiny change (typo, copy, rename): lint/format + typecheck. No spec/contract check needed.
- Normal change (behavior/feature): unit tests + typecheck + lint + boundary spot-check (resilience/security/observability where touched) + cleanup.
- Big change (cross-service, migration): full verification (tests + typecheck + lint + build + dependency scan) + spec/contract alignment check + executive + engineer packets.
- Refactor (no behavior change): characterization tests pass before and after + typecheck + lint. No new spec artifacts unless contracts changed.
- Security-sensitive change: add security spot-check (authn/authz, input validation, safe logging) even for normal scope.
Inputs / Outputs
Inputs: All prior skill outputs from the current workflow; verification commands (tests, typecheck, lint, build); archobs baseline (for regression check). Outputs: Executive packet (decision bandwidth), engineer packet (implementation bandwidth), learning loop. Terminal skill — nothing consumes its output downstream.
Workflow
- Re-check intent artifacts:
- if contracts/semantics changed: specs/contracts are updated (
spec) - if shared primitives were added/changed: API surface + adoption notes are clear (
platform) - for non-trivial work: objective function, measurement ladder, and kill criteria are documented
- if 2+ viable approaches existed: decision table includes assumptions (facts vs assumptions) and opportunity costs
- if contracts/semantics changed: specs/contracts are updated (
- Run verification (prefer narrow → broad):
- unit tests / focused tests
- typecheck
- lint/format (if configured)
- dependency/security scan (if configured)
- build (if relevant)
- Boundary discipline spot-check (only where the change touched boundaries):
- timeouts/cancellation/retry safety (
resilience) - authn/authz + input validation + safe logging (
security) - logs/traces/metrics correlation + low-cardinality labels (
observability) - architecture health regression (skip for tiny changes — typo, copy, single-file rename): run
archobs report --suggestions-provider rulesand wait for the report to complete — then runarchobs show summary --format jsonandarchobs show risks --top 5 --format jsonto verify that top file risk scores and cluster leakage did not increase compared to the previous run; if no prior.archobs/baseline exists, create one now so future runs can detect regressions (archobs)
- timeouts/cancellation/retry safety (
- Cleanup:
- remove dead code, debug logs, commented-out blocks
- ensure errors are actionable and don’t leak secrets/PII
- update quickstarts or runbooks if needed
GATE: Verification (step 2) must have actually been executed — commands run with results captured. "Tests pass" without showing which commands ran and their output does not satisfy this gate. If verification could not be run, report "not run" and why.
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.
- 9d ago First seen · 117 lines · 72 tokens per session scan A 0f150287af88
finish is a skill published in the GitHub repository bricerising/enterprise-software-playbook (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 72 tokens to every session and 1,738 once invoked, about $0.0004 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
replit-deck
For product and technical management work: turn PRDs, roadmaps, RFCs, architecture reviews, and retros into decision documents. Built around the core query "pm-feature-business-case-deck", with product strategy lead judgment, buyer-ready proof, and this outcome: approve the feature, architecture, roadmap, or incident…
hps-true-blueprint
OpenDesign's engineering blueprint: how the sandbox, sidecar, and daemon fit — the system diagram and the invariants. Built as a decision-grade product management deck for engineering org.
html-ppt-knowledge-arch-blueprint
OpenDesign's incident retro: the daemon-restart data bug, the root cause, the fix, and the systemic follow-ups. Built as a decision-grade product management deck for engineering, SRE, leadership.
deck-open-slide-canvas
OpenDesign's architecture review: the local daemon + agent-runtime design, the tradeoffs, and the decision to lock. Built as a decision-grade product management deck for staff eng, tech leads, security.
architecture-aware-init
Selects architecture paradigm via research before scaffolding. Use when architecture is undecided and the choice needs justification and documentation.
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…