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 cambridgetcg/agenttool --skill inspect-agent-surfaces-hermesgit clone --depth 1 https://github.com/cambridgetcg/agenttoolWrote 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/cambridgetcg/agenttool/inspect-agent-surfaces-hermes)<a href="https://agentmods.dev/skills/cambridgetcg/agenttool/inspect-agent-surfaces-hermes"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/inspect-agent-surfaces-hermes/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/cambridgetcg/agenttool/inspect-agent-surfaces-hermes"><img src="https://agentmods.dev/badge/skills/cambridgetcg/agenttool/inspect-agent-surfaces-hermes.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 | $0.00079 | $0.00449 |
| Opus 5 | $0.00039 | $0.00225 |
| Sonnet 5 | $0.00016 | $0.00090 |
| Haiku 4.5 | $0.00008 | $0.00045 |
Grade A, and why
inspect-agent-surfaces-hermes 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.
What it actually says
Inspect Agent Surfaces from Hermes
Register the Telescope stdio MCP server under the exact Hermes name
agenttool-telescope, then call
mcp_agenttool_telescope_telescope_scan with one public fully qualified domain
or HTTPS origin. Reject paths, queries, fragments, credentials, IP literals,
and non-standard ports without repeating secret-bearing input values.
Treat the result as evidence:
sourcesare bounded transport observations.surfacesmap those observations into advertised discovery surfaces.claimsretain theirbasis,role,taint, and evidence references.actionsare inert plans and must never be run automatically.diagnosticsandboundary_codesqualify every conclusion.
Separate observed evidence, publisher assertions, local inferences, and unknowns. A present advertisement does not prove identity, ownership, authorization, availability, a successful MCP or A2A handshake, safety, permission, endorsement, or fitness.
Telescope makes a fixed bounded set of credential-free public HTTPS GETs. It does not follow discovery roads or catalog targets, invoke advertised endpoints, send credentials, download artifacts, install packages, or run generated commands. DNS preflight does not pin the connected socket and is not a universal hosted-service SSRF boundary. Blanket consent given before discovery is not target-specific installation authority; disclose the exact artifact and verification plan before requesting fresh authorization.
These prefixed names require the Hermes MCP server name agenttool-telescope.
If mcp_agenttool_telescope_telescope_scan is unavailable, identify the
missing MCP connection or exact tool and use only an explicitly named fallback.
Never imply that a scan, handshake, verification, download, or installation
occurred when it did not.
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 · 41 lines · 79 tokens per session scan A 46fe9231c3a8
inspect-agent-surfaces-hermes is a skill published in the GitHub repository cambridgetcg/agenttool (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 449 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
add-a-service
Scaffold a new service under services/ in the builders-stack monorepo. Use when something needs its own URL, port, or independent deploy. Covers the package, entrypoint, config, Tilt, deployment registry, and shared small-image build path.
design-a-schema
Model a new table (or reshape an existing one) in libs/db with Drizzle — normalize by default, add the right constraints, and index deliberately. Use when adding a table/column, deciding on keys and foreign keys, or when a query is slow because the schema or its indexes are wrong. Enforces the stack's "Drizzle is the…
wire-a-new-payment-provider
Add or swap a payment provider behind the @stack/payment adapter in the builders-stack monorepo. Use when integrating Stripe, Paddle, Lemon Squeezy, or any provider alongside or in place of the default Creem adapter. The whole point is that apps and the API never change — only the adapter implementation does. Covers…
add-a-lib
Scaffold a new shared library under libs/ in the builders-stack monorepo. Use when code is needed in two or more places (apps or services) and should become a single source of truth consumed by package name. Covers the package.json, tsconfig, the one-public-door src/index.ts barrel, and wiring it into a consumer…
optimize-a-query
Diagnose and fix a slow Postgres query in the builders-stack — read its EXPLAIN plan, find the missing index or the ORM N+1, and confirm the fix. Use when a page or endpoint is slow, a query times out, or pgstatstatements shows a hot query. Pairs with design-a-schema for the index itself.
create-a-worktree
Create, inspect, or retire an isolated Builders Stack agent runtime through Worktree Zero. Use whenever parallel work needs another checkout or an old worktree needs cleanup.