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 BlackBeltTechnology/pi-agent-dashboard --skill pre-scaffold-openspec-coherence-checkgit clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboardWrote 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/blackbelttechnology/pi-agent-dashboard/pre-scaffold-openspec-coherence-check)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/pre-scaffold-openspec-coherence-check"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/pre-scaffold-openspec-coherence-check/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/blackbelttechnology/pi-agent-dashboard/pre-scaffold-openspec-coherence-check"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/pre-scaffold-openspec-coherence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.01356 |
| Opus 5 | $0.00040 | $0.00678 |
| Sonnet 5 | $0.00016 | $0.00271 |
| Haiku 4.5 | $0.00008 | $0.00136 |
Grade A, and why
pre-scaffold-openspec-coherence-check 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to Use
Use before scaffolding any new OpenSpec change in this project, regardless of whether the topic feels novel. Two of the most damaging mistakes the assistant has made are (a) re-proposing work that already shipped and was archived, and (b) basing claims about current code on stale file-index harvests or grep results that miss the actual wiring idiom. This skill front-loads the cheap checks that would have caught both.
Trigger this skill when about to run any of: openspec change new, Write to openspec/changes/<name>/proposal.md, the openspec-new-change skill, the openspec-ff-change skill, or any drafted "## Why / ## What Changes" markdown that will become a proposal.
Do NOT skip even when the explore-mode conversation feels grounded. The Explore subagent harvests the file-index which can be days stale; the main agent's own grep can answer the wrong question (e.g. grepping for a consumer component when the wiring is inline).
Procedure
- Archive sweep: ls openspec/changes/archive/ | grep -iE ‘<topic-keywords>’. For tool-renderer / plugin-slot / MCP / ctx_* / context-mode topics specifically check for 2026-06-05-wire-tool-renderer-slot and 2026-06-05-add-ctx-tool-renderer. If any archive entry matches the topic, READ its proposal.md before writing a new one.
- Active sweep: openspec list | grep -iE ‘<topic-keywords>’. Read any active change that overlaps so the new proposal does not collide on filename, capability, or scope.
- Current-code verification (for behaviour claims): if the proposal says ‘X is not wired’, ‘Y never fires’, ‘Z falls through to Generic’, grep for the FUNCTIONAL pattern not just the named component. For tool-renderer claims specifically: grep -rn 'getClaims.*tool-renderer\|forToolName' packages/client/src/components/ToolCallStep.tsx and read the current dispatch block (lines 90–120). The slot wiring inlines useSlotRegistryOrNull + forToolName + claimShouldRender; the ToolRendererSlot consumer component is unused, but that does NOT mean the slot is unwired.
- Slot-prop contract check: cat packages/shared/src/dashboard-plugin/slot-props.ts and read SlotPropsMap[‘<slot>’]. Confirm the required fields (every slot requires pluginContext: AnyPluginContext) and the optional fields. Do not invent a contract.
- Registry check (built-in renderers): cat packages/client/src/components/tool-renderers/registry.ts. The ctx_* family is mapped to a single CtxToolRenderer with a ctx_-prefix safety net for new tool names. Honour this architecture choice unless explicitly proposing to revisit it.
- Architecture-choice review: when the topic intersects an existing implementation, search recent commits with git log --oneline --since=<30 days> -- <relevant paths> to understand which design the team picked and the rationale. The choice between core built-in vs plugin for ctx_* was DELIBERATE (high-frequency tool, hot path); do not propose to reverse it without an explicit justification section.
- Optional but recommended: run the spec-coherence-check skill (project skill) which sweeps all active proposals for staleness, conflicts, and obsolescence against the current codebase and archived changes. Treat its output as authoritative.
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 · 37 lines · 80 tokens per session scan A 5e0ec86c76fd
pre-scaffold-openspec-coherence-check is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (280 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 1,356 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 2026-09-03.
Other skills, from other repositories
goga-cookbook
Principles for applying DSL specification in cell and CODEMANIFEST design.
goga-plan-by-design
Compile a design document into a ralphex execution plan.
goga-review-plan
Verify execution plan completeness and correctness.
goga-brainstorm
Pipeline orchestrator for brainstorming the cells architecture.
goga-define-challenge
Challenge the complete product definition before the PRD is generated.
goga-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.