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 spec-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/spec-coherence-check)<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/spec-coherence-check"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/spec-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/spec-coherence-check"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/spec-coherence-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 487 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.04233 |
| Opus 5 | $0.00040 | $0.02116 |
| Sonnet 5 | $0.00016 | $0.00847 |
| Haiku 4.5 | $0.00008 | $0.00423 |
Grade A, and why
spec-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 6d 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze active OpenSpec proposals against the current codebase state, detect staleness / conflicts / obsolescence, and orchestrate updates.
Input: Optional --proposal <name> for single-proposal mode.
No arguments = full sweep of all active proposals.
Phase 1: Sweep Report
Step 1 — Gather context
a) Get all active proposals:
openspec list --json
If --proposal <name> was provided, filter to just that proposal.
b) List all archived changes:
ls openspec/changes/archive/
Parse archive directory names to extract dates. Format is YYYY-MM-DD-<name>.
Extract the first 10 characters as the date string.
c) Date each active proposal using this fallback chain:
-
Git first-commit date:
git log --follow --diff-filter=A --format='%ai' -- "openspec/changes/<name>/proposal.md" | tail -1Parse the date portion (first 10 chars:
YYYY-MM-DD). -
If empty (file is untracked), use filesystem birthtime:
- macOS:
stat -f "%SB" -t "%Y-%m-%d" "openspec/changes/<name>/proposal.md" - Linux:
stat -c "%W" "openspec/changes/<name>/proposal.md"(convert epoch to date)
- macOS:
-
If still unknown, use the oldest archive date as a floor estimate.
d) Read artifacts for each active proposal.
Read only the files that exist — not all proposals have all artifacts:
openspec/changes/<name>/proposal.md(always exists)openspec/changes/<name>/design.md(if exists)openspec/changes/<name>/tasks.md(if exists)openspec/changes/<name>/specs/directory (if exists)
From each proposal, extract and note:
- Referenced files: paths matching
src/...in Impact and body text - Referenced capabilities: from
### Modified Capabilitiesand### New Capabilities - Assumptions: statements in Context sections, Non-Goals, and design decisions
- Files touched: from
## Impactsection specifically
e) Read relevant archived changes.
For each active proposal, identify archives dated after its creation date.
For each such archive, read its proposal.md and extract:
## What Changes— summary of modifications## Capabilities— look forBREAKINGmarkers,Modified,Removedentries## Impact— files and components touched
What ships with it
2 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.
- 6d ago First seen · 497 lines · 80 tokens per session scan A 178ce409727e
spec-coherence-check is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (278 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 4,233 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-define-experience
Define the user experience required to achieve the established product goals and solve the identified problem.
goga-review-plan
Verify execution plan completeness and correctness.
goga-accept-manifest-review
Verify each Cell's CODEMANIFEST against the implementation.
goga-cells-by-brainstorm
Creation and modification of cells by architecture plan.