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 agentmods add commands/geckovision/gecko-surf/make-agent-readygit clone --depth 1 https://github.com/GeckoVision/gecko-surfWrote 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/commands/geckovision/gecko-surf/make-agent-ready)<a href="https://agentmods.dev/commands/geckovision/gecko-surf/make-agent-ready"><img src="https://agentmods.dev/badge/commands/geckovision/gecko-surf/make-agent-ready.svg" alt="Measured on agentmods" 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 | $0.00061 | $0.00747 |
| Opus 5 | $0.00030 | $0.00374 |
| Sonnet 5 | $0.00012 | $0.00149 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
make-agent-ready 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/make-agent-ready
Run the five-step onboarding spine on a provider's API and emit the served MCP + the one-click add + the discovery breadcrumbs. Aggregate, not replace.
Argument: an OpenAPI 3.x URL, a docs page URL, or a pasted spec.
Step 0 (if the provider is still building/hardening the API): before comprehending,
walk the agent-readiness best-practices checklist so the surface itself is unambiguous
— one canonical read, field-complete, clear enums/required fields, a machine-authable
auth path. This is provider-side design work, upstream of the steps below. (See
skills/api-agent-ready/best-practices.md.)
Steps
- Comprehend. If it's an OpenAPI URL, run
gecko <url>. If it's a docs page, rungecko from-docs <url>to recover a draft spec first, then comprehend. Report the engine's live counts: operations ingested / tools surfaced / auth-gated hidden. (Seeskills/api-agent-ready/comprehend.md.) - Serve MCP.
gecko servestands up a Streamable-HTTP MCP for the full surface. Hand over the one-click add —claude mcp add --transport http <name> <url>plus the Cursor / VS Code deeplinks. (Seeskills/api-agent-ready/serve-mcp.md.) - Emit breadcrumbs (Building). Hand-author
llms.txt+gecko.json(and optionalx-geckospec annotations) for the provider to drop at their origin. State clearly thatgeckodoes not auto-emit these yet. (Seeskills/api-agent-ready/artifacts.md.) - Make discoverable. Breadcrumb-based, provider-hosted — not a public catalog.
(See
skills/api-agent-ready/discoverable.md.) - Confirm aggregate-not-replace. State explicitly that the provider's own MCP is
untouched and runs side by side. (See
skills/api-agent-ready/aggregate-not-replace.md.)
The engine
pip install "gecko-surf[serve]"
gecko https://api.example.com/openapi.json # comprehend + serve
# or, zero-install:
uvx --from "gecko-surf[serve] @ git+https://github.com/GeckoVision/gecko-surf" \
gecko https://api.example.com/openapi.json
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 · 58 lines · 61 tokens per session scan A 366155c960e2
make-agent-ready is a command published in the GitHub repository GeckoVision/gecko-surf (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 61 tokens to every session and 747 once invoked, about $0.0003 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.