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 osovv/grace-marketplace --skill grace-explainergit clone --depth 1 https://github.com/osovv/grace-marketplaceWrote 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/osovv/grace-marketplace/grace-explainer)<a href="https://agentmods.dev/skills/osovv/grace-marketplace/grace-explainer"><img src="https://agentmods.dev/badge/skills/osovv/grace-marketplace/grace-explainer/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/osovv/grace-marketplace/grace-explainer"><img src="https://agentmods.dev/badge/skills/osovv/grace-marketplace/grace-explainer.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 | $0.00030 | $0.00293 |
| Opus 5.5 | $0.00012 | $0.00117 |
| Sonnet 5.5 | $0.00006 | $0.00059 |
| Haiku 4.5 | $0.00003 | $0.00029 |
Grade A, and why
grace-explainer 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.
What it actually says
.grace/contextstores requirements, technology, principles, deployment, and UX constraints..grace/graphstores graph indexes and routed graph documents withGD-*,M-*, andDF-*tags..grace/verificationstores verification indexes and routedV-M-*entries..grace/changesstores active and archivedC-*change bundles withGraceChangeSpec, optional non-normative design context, andGraceChangePlan. </core_model>
What ships with it
6 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.
- 1mo ago First seen · 25 lines · 30 tokens per session scan A a6f27bee9ae1
grace-explainer is a skill published in the GitHub repository osovv/grace-marketplace (254 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 293 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
all-hands
Convene the relevant SpecRoute implementation agents to plan, collaborate, implement, and review a piece of work end-to-end. Engages only the specialists the work actually touches, runs autonomously through planning into implementation and review, and accepts free-text work or a path to a PRD / spec / issue file.…
doc-currency-check
Audit SpecRoute's documentation for staleness against reality - vendor facts, version anchors, dates written in the wrong tense, counts that no longer match disk, and claims mirrored inconsistently across the four vendor-matrix copies. Use before a release, after any vendor ships a breaking change, or on a scheduled…
audit-artifact
Interactive workflow for auditing a SpecRoute artifact before it is treated as implementation-ready. Use when checking a PRD, spec triplet, prompt set, agent file, skill, command, hook, rule, or runtime layout. Asks which artifact path to inspect and which contract to apply. Triggers - "audit this artifact", "check…
frontmatter-lint
Validates YAML frontmatter across SpecRoute artifacts (agents, skills, commands) against the per-artifact contract. Reports missing required fields, malformed YAML, and drift between similar artifacts. Use proactively before commits, when reviewing PRs, or when an agent/skill/command isn't loading correctly.
add-vendor
Interactive workflow for adding a new agent CLI vendor to the SpecRoute supported matrix. Walks through scaffolding the runtime layout, adding the vendor's row to the matrix table, creating the per-vendor rule file, wiring MCP rendering (if applicable), and updating cross-vendor sync. Use when proposing or…
scaffold-artifact
Interactive scaffolding for any SpecRoute artifact (PRD, spec, agent, skill, command, hook, prompt, runtime layout). Asks for artifact type and vendor (where applicable), copies the canonical template, generates the directory structure, and pre-fills the frontmatter. Use when starting a new artifact under prds/…