Borrowing it
Nothing to install: this file belongs to surveycto/surveycto-agent-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/surveycto/surveycto-agent-skill/develop/AGENTS.mdgit clone --depth 1 https://github.com/surveycto/surveycto-agent-skillWrote 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/instructions/surveycto/surveycto-agent-skill/agents-md)<a href="https://agentmods.dev/instructions/surveycto/surveycto-agent-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/surveycto/surveycto-agent-skill/agents-md.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 | $0.03355 | $0.03355 |
| Opus 5 | $0.01677 | $0.01677 |
| Sonnet 5 | $0.00671 | $0.00671 |
| Haiku 4.5 | $0.00335 | $0.00335 |
Grade A, and why
surveycto-agent-skill AGENTS.md 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 8d 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on this repo
This file orients an AI agent (or a human) making changes to the
SurveyCTO Agent Skill itself. It is not part of the skill bundle —
it is excluded from surveycto-skill.zip / surveycto-skill-dev.zip.
For end-user-facing documentation see README.md. For the
skill content itself see SKILL.md.
What this repo is
An Agent Skills package that gives AI agents
SurveyCTO domain expertise. The deliverable is a zip
(surveycto-skill.zip) that hosts (Claude Cowork, Codex, etc.) extract
into their skills directory. The zip is not committed — it's built
and published by GitHub Actions:
- Push to
develop→.github/workflows/build-dev.ymlbuildssurveycto-skill-dev.zipas a workflow artifact (downloadable from the run page) for smoke-testing pre-release changes. - Push to
main→.github/workflows/release.ymlbuildssurveycto-skill.zipand attaches it to a new GitHub Release whose tag/name comes frommetadata.versioninSKILL.md.
For local smoke-testing, you can build a zip yourself (see When to rebuild the local zip). It stays in your working tree and is gitignored.
Branching
develop— active development. Pushes here trigger the dev-build workflow.main— stable releases. Pushes here trigger the release workflow.
Default working branch for new work is develop (or a feature branch
off develop). PRs target develop first; develop → main is reserved
for release.
When to bump the version
The release workflow takes its tag from metadata.version in
SKILL.md. If develop is merged into main without a bump since the
last release, the workflow will try to re-tag the same version and the
release will fail (or, worse, silently overwrite, depending on settings).
Procedure before making non-trivial changes to skill content
(SKILL.md, references/, assets/):
- Compare the current branch's
metadata.versioninSKILL.mdagainstmain's:git show origin/main:SKILL.md | sed -n '/^metadata:/,/^---/p' | grep version - If the two match, the current branch hasn't been bumped since the
last release — bump it as part of this change. If they already
differ (current is ahead of
main), no further bump is needed unless the new change crosses a different semver boundary than the bump that's already there. - If you're unsure (e.g. the change is small, or the user hasn't asked), ask or offer rather than skipping. A missed bump blocks release; an unnecessary bump is harmless.
- When bumping, update both places the version appears in
SKILL.md(see below). They must stay in sync — the frontmatter drives the release tag and the body line is what the agent reports at runtime, since agents don't see frontmatter.
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.
- 8d ago First seen · 279 lines · 3,355 tokens per session scan A 73c36005ec1a
surveycto-agent-skill AGENTS.md is an instructions file published in the GitHub repository surveycto/surveycto-agent-skill (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,355 tokens to every session, about $0.0168 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.