Borrowing it
Nothing to install: this file belongs to Southclaws/storyden. 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/Southclaws/storyden/main/AGENTS.mdgit clone --depth 1 https://github.com/Southclaws/storydenWrote 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/southclaws/storyden/agents-md)<a href="https://agentmods.dev/instructions/southclaws/storyden/agents-md"><img src="https://agentmods.dev/badge/instructions/southclaws/storyden/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/southclaws/storyden/agents-md"><img src="https://agentmods.dev/badge/instructions/southclaws/storyden/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 | $0.01692 | $0.01692 |
| Opus 5.5 | $0.00677 | $0.00677 |
| Sonnet 5.5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
storyden 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 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Purpose
This file is the generic entrypoint for finding project documentation relevant to the current task. Use this as an index, then open only the docs needed for the work at hand.
Quick Orientation
- Product and scope:
README.mdfor product overview and goals.web/is the product application.home/is the website/docs app (only use when task targets docs/marketing site).
- Backend high-level direction (Go):
cmd/backend/main.gois the backend runtime entrypoint.app/resources/**,app/services/**,app/transports/**are the core 3 layers (data, business logic, external interfaces).internal/**contains infrastructure and platform integration code.api/openapi.yamlandapi/rpc/**are contract/spec roots for generated transport code.internal/ent/schema/**is the DB schema source of truth.
- Local setup and workflow:
Taskfile.ymlfor canonical project task commands.
- Architecture and backend:
CLAUDE.mdfor high-level architecture map, layering rules, and command guardrails.docs/architecture/for deeper architecture notes when needed.internal/config/config.yamlfor runtime configuration surface.
- Frontend and design system (
web):- Read
web/AGENTS.mdbefore editing frontend code. Its Storybook and component-reuse rules are the required frontend entrypoint. web/panda.config.tsfor Panda setup, tokens, recipes, patterns, and conditions.web/src/theme/andweb/src/app/global.cssfor semantic tokens and global styling rules.web/src/app/(dashboard)/**/README.mdfor route/domain intent.
- Read
- API and SDK:
api/openapi.yamlas API contract source of truth.api/rpc/README.mdandsdk/**/README.mdfor transport/SDK usage.
Backend Task Routing (Go)
Storyden backend is a Go application using Uber Fx dependency injection and a 3-layer app structure.
- Runtime composition and startup:
cmd/backend/main.gowiresconfig,infrastructure,resources,services, andtransports.app/resources/resources.go,app/services/services.go, andapp/transports/transports.godefine dependency module composition.
- Layer responsibilities:
app/resources/**: persistence/data access and query/write repositories.app/services/**: business logic and orchestration.app/transports/**: external interfaces (HTTP OpenAPI, RPC, MCP).internal/**: infrastructure and platform concerns (db, cache, mail, pubsub, vector, config, etc.).
- If your task is API endpoint behavior:
- Start in
app/transports/http/bindings/**for handlers/bindings. - Check generated types/server in
app/transports/http/openapi/**. - Update API contract in
api/openapi.yaml(and relatedapi/common/**schemas) when request/response surface changes.
- Start in
- If your task is domain/business logic:
- Implement changes in
app/services/<domain>/**. - Use
app/resources/<domain>/**for data access changes needed by that logic.
- Implement changes in
- If your task is database/schema/persistence:
- Source of truth is
internal/ent/schema/**. - Regenerated artifacts are under
internal/ent/**.
- Source of truth is
- If your task is infra/config wiring:
internal/infrastructure/**for adapters and integrations.internal/config/config.yamlfor environment-backed runtime configuration.
- If your task is plugins/RPC:
- RPC schemas:
api/rpc/**andapi/plugin.yaml. - Transport/runtime implementation:
app/transports/rpc/**,app/services/plugin/**,app/resources/plugin/**.
- RPC schemas:
- If your task is MCP tools:
app/transports/mcp/**andapp/transports/mcp/tools/**.
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 Changed · +1 lines · +34 tokens per session a0b24ae7f795
- 2mo ago First seen · 114 lines · 1,658 tokens per session scan A c9350e96016a
storyden AGENTS.md is an instructions file published in the GitHub repository Southclaws/storyden (346 stars, last pushed 3d ago), licensed MPL-2.0. It adds 1,692 tokens to every session, about $0.0068 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.
storyden AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| storyden AGENTS.mdSouthclaws/storyden | Instructions file | 346 | 3d ago | MPL-2.0 | A | 1,692 | 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 | today | 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 |