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 ArtemioPadilla/agent-triforce --skill business-reviewgit clone --depth 1 https://github.com/ArtemioPadilla/agent-triforceWrote 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/artemiopadilla/agent-triforce/business-review)<a href="https://agentmods.dev/skills/artemiopadilla/agent-triforce/business-review"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/business-review/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/artemiopadilla/agent-triforce/business-review"><img src="https://agentmods.dev/badge/skills/artemiopadilla/agent-triforce/business-review.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 | $0.00047 | $0.02014 |
| Opus 5 | $0.00023 | $0.01007 |
| Sonnet 5 | $0.00009 | $0.00403 |
| Haiku 4.5 | $0.00005 | $0.00201 |
Grade A, and why
business-review 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 12d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run a post-implementation business review for: $ARGUMENTS
This skill closes the product loop. After Dev implements and QA verifies, you assess whether the implementation delivers the business value promised in the spec.
Follow these steps:
SIGN IN:
- Run the SIGN IN checklist from your agent file
- Read the feature spec from
docs/specs/{feature-name}.md - Read Centinela's review from
docs/reviews/if available (security audit, code review, or release check) - Identify the acceptance criteria, success metrics, scope boundaries, and risks to assess
- Note any open product decisions flagged by Centinela
BUSINESS ASSESSMENT:
Evaluate each of the following 5 areas. For each one, record: status (MET/NOT MET), evidence, and notes.
Area 1 -- Success Metrics
- Read the spec's
## Success Metricssection - For each KPI: assess whether the implementation enables measurement and achievement
- If KPIs cannot be measured with the current implementation, note what's missing
- Record: MET if implementation enables all stated KPIs, NOT MET otherwise
Area 2 -- Scope Compliance
5. Read the spec's ## Scope section (In Scope and Out of Scope)
6. Verify every In-Scope item has been addressed in the implementation
7. Verify no Out-of-Scope items were implemented (scope creep)
8. Note any In-Scope items that were descoped and whether the rationale was documented
9. Record: MET if scope was respected, NOT MET if items are missing or scope crept
Area 3 -- Acceptance Criteria Business Validation 10. Read the spec's acceptance criteria (GIVEN/WHEN/THEN) 11. For each AC: assess whether a technical pass actually delivers the stated business value 12. Flag any ACs that could pass technically but fail the business intent (e.g., "user can log in" passes but the UX is unusable) 13. Record: MET if all ACs deliver business value, NOT MET if any are technically passing but business-failing
Area 4 -- Risk Review
14. Read the spec's ## Risks & Rollback section
15. For each identified risk: did it materialize? If yes, was the mitigation applied?
16. Are the rollback criteria still valid and actionable?
17. Note any new risks discovered during implementation that weren't in the spec
18. Record: MET if risks were properly managed, NOT MET if unmitigated risks remain
Area 5 -- Product Decisions
19. Check Centinela's review for "areas where product decisions are needed"
20. Check the spec's ## Open Questions — are any still unresolved?
21. For each open decision: provide a recommendation or escalate to the user
22. Record: MET if all decisions are closed, NOT MET if blocking decisions remain open
⏸️ TIME OUT — Business Verification (DO-CONFIRM): Run the Business Verification checklist from your agent file.
CONFIDENCE SCORE CALCULATION:
Calculate the business confidence score:
- For each of the 5 areas: 20 points if MET, 0 points if NOT MET
- Confidence score = sum of all area scores (integer, 0-100)
VERDICT:
- If ALL areas MET: APPROVED with confidence score
- If 1-2 non-critical areas NOT MET: CONDITIONALLY APPROVED with specific remediation steps
- If any critical area NOT MET (Success Metrics or AC Business Validation): CHANGES REQUIRED with required actions
PROJECT TIMELINE & ROADMAP VISUALIZATION:
After completing the assessment, generate visual representations of the project timeline and roadmap using Mermaid diagrams. These render natively on GitHub, VS Code, and most documentation platforms.
- Feature Timeline — Generate a Mermaid Gantt chart showing the feature's lifecycle phases with actual dates:
- Gather dates from: spec file (creation date), git log (first implementation commit, last commit), review files (review dates), and this business review date
- Include phases: Spec Draft, Spec Approved, Implementation, QA Review, Business Review
- Mark the current phase as active
- Example format:
```mermaid gantt title Feature Timeline: {feature-name} dateFormat YYYY-MM-DD section Specification Spec Draft :done, spec, {spec-start}, {spec-end} Spec Approved :done, approve, {approve-date}, 1d section Implementation Development :done, dev, {dev-start}, {dev-end} section Review QA Review :done, qa, {qa-start}, {qa-end} Business Review :active, biz, {biz-date}, 1d ```
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.
- 12d ago First seen · 214 lines · 47 tokens per session scan A c75ecf3cfd0c
business-review is a skill published in the GitHub repository ArtemioPadilla/agent-triforce (3 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 2,014 once invoked, about $0.0002 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
missive
Invoke only when spawning a quest from a GitHub issue reference. Fetches GitHub issue context for quest spawning. Parses issue references, retrieves structured data via gh, and produces branch suggestions and PR keywords. Used standalone or as input to quest orchestration.
openspec-bulk-archive-change
Archive multiple completed changes at once. Use when archiving several parallel changes.
openspec-continue-change
Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.