Borrowing it
Nothing to install: this file belongs to techtankto/techtank-site. 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/techtankto/techtank-site/main/AGENTS.mdgit clone --depth 1 https://github.com/techtankto/techtank-siteWrote 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/techtankto/techtank-site/agents-md)<a href="https://agentmods.dev/instructions/techtankto/techtank-site/agents-md"><img src="https://agentmods.dev/badge/instructions/techtankto/techtank-site/agents-md/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/instructions/techtankto/techtank-site/agents-md"><img src="https://agentmods.dev/badge/instructions/techtankto/techtank-site/agents-md.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 | $0.02837 | $0.02837 |
| Opus 5.5 | $0.01135 | $0.01135 |
| Sonnet 5.5 | $0.00567 | $0.00567 |
| Haiku 4.5 | $0.00284 | $0.00284 |
Grade A, and why
techtank-site 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 27d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for any coding agent working in this repository, and the primary,
tool-agnostic context source for all of them (Claude Code, Cursor, Copilot,
Codex). Tool-specific files like CLAUDE.md defer to it.
What this repo is
A Next.js (App Router) implementation of techtankto.com, Toronto's volunteer-run tech community website. It funnels visitors into roles: attendee, speaker, host, sponsor, or volunteer.
The PRD (docs/prd/) is a historic record of how the current structure came
to be. Read it for context on prior decisions (why a route was shaped that
way, what a design token replaced), not as a spec to keep in sync.
House standards live in the vendored skills and load via skill discovery; see
§House standards. Application code lives in app/, with shared pieces in
components/, constants/, and public/. The initial UI scaffold was
generated from the prior PRD via
v0.
For developer-facing setup (scripts, directory tree, route map), see
README.md.
Repository layout
.
├── AGENTS.md # Primary agent context
├── CLAUDE.md # Claude Code stub that includes AGENTS.md
├── .agents/skills/ # vendored house-standard skills (copied, portable)
├── .claude/skills/ # same skills (symlinked to .agents/skills/)
└── docs/
└── prd/ # 01-brief → 06-plan, the numbered pipeline
docs/prd/06-plan.md records the milestone list as it stood during the
redesign. docs/prd/03-solution.md records the original route map and
per-surface content requirements; README.md is the current route reference.
How the information architecture works
A conversion-oriented onboarding hub, not a flat "link-tree" layout.
README.md carries the current route map; docs/prd/03-solution.md carries
the shared layouts and navigation as originally specified:
/: social-proof-driven home (testimonials, event photos, logo cloud)./about(+/about/faq,/about/team): values manifesto built on four pillars, Community, Innovation, Teamwork, Respect; FAQ; team roster./get-involved: onboarding hub with four role sub-pages (Speaker, Host, Sponsor, Organizer Team), each ending in an intake action (email us at[email protected])./events: embedded Luma calendar./donate: Stripe and Interac e-transfer donation info. It stays a top-level route rather than nesting under/get-involved, since it is not a role intake form, but the/get-involvedsub-nav and the footer link it as part of that grouping./resources/media-kit: standalone brand assets and fast facts for media./resources/design-system: brand guidelines and design-token reference./legal: grouped compliance documents.
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.
- 27d ago Changed · +63 lines · +963 tokens per session 3bf9ae268e6f
- 28d ago Changed · +10 lines · +154 tokens per session 031f8377fd6d
- 1mo ago Changed · +7 lines · +206 tokens per session a2fda802575a
- 1mo ago Changed · -28 lines · -385 tokens per session 543ad43d618e
- 2mo ago Changed · +7 lines · +113 tokens per session fcff4ebfb20a
- 2mo ago First seen · 153 lines · 1,786 tokens per session scan A 53992fef5fa9
techtank-site AGENTS.md is an instructions file published in the GitHub repository techtankto/techtank-site (5 stars, last pushed 3d ago), licensed MIT. It adds 2,837 tokens to every session, about $0.0113 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 2026-08-31.
techtank-site AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| techtank-site AGENTS.mdtechtankto/techtank-site | Instructions file | 5 | 3d ago | MIT | A | 2,837 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |