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 instructions/lindoelio/spec-driven-steroids/agents-mdgit clone --depth 1 https://github.com/lindoelio/spec-driven-steroidsWrote 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/lindoelio/spec-driven-steroids/agents-md)<a href="https://agentmods.dev/instructions/lindoelio/spec-driven-steroids/agents-md"><img src="https://agentmods.dev/badge/instructions/lindoelio/spec-driven-steroids/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 | $0.01263 | $0.01263 |
| Opus 5 | $0.00632 | $0.00632 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
spec-driven-steroids 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 5d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Identity
This is Spec-Driven Steroids (spec-driven-steroids), a CLI tool and template bundle that injects approval-gated brief and full Spec-Driven workflows into AI coding tools. It ships as a single public npm package with a sds alias.
Technology Stack
- Language: TypeScript 5.9, ES2022 target, NodeNext modules, strict mode
- Runtime: Node.js >=20
- Package Manager: pnpm 10 (workspace monorepo)
- CLI: Commander.js 11 + Inquirer 9 + Chalk 5
- Testing: Vitest 2.x with v8 coverage
- Build:
tsc(no bundler) - Publishing: Changesets → npm (with provenance)
See ARCHITECTURE.md for system boundaries and STYLEGUIDE.md for code conventions.
Essential Commands
pnpm build # Build all packages
pnpm test # Run all tests (requires prior build)
pnpm typecheck # Type-check all packages (no emit)
pnpm lint # Lint all packages
pnpm test:coverage # Run tests with coverage
pnpm changeset # Create a changeset entry
When writing code here, always run pnpm typecheck before considering a change complete.
Agent Constraints
- Code comments policy: Add code comments only when they are highly necessary to explain non-obvious intent, workarounds, or critical constraints. Do not add comments that merely restate what the code does.
- Import style: Use ES module imports only. All packages are
"type": "module". Use.jsextensions in relative imports (TypeScript resolves them correctly). - Source layout: The CLI source lives in
packages/cli/src/. Tests live inpackages/cli/tests/(not co-located). Shared test utilities are inpackages/test-utils/src/. - Build before test: Integration tests import from
dist/, sopnpm build(ortsc) must run beforepnpm test. - Package scope: The
packages/clipackage is the only public package.packages/test-utilsandpackages/landing-pageare private. - Platform template changes: When editing template files under
packages/cli/templates/, ensure corresponding E2E tests inpackages/cli/tests/integration/are updated because many tests verify template content assertions. - Template source: When adding or modifying template files, update
STEROIDS_SKILL_DIRSandSTEROIDS_FILESinpackages/cli/src/cli/index.tsif the new files must be tracked for clean and injection. - Approval-gated SDS invocation: When SDS is selected, implementation must follow an approved
brief.mdor the approved full flow (requirements → design → tasks → implementation). Direct implementation belongs to the host harness outside SDS. See CONTRIBUTING.md for the PR process. - Spec artifact exclusion: Never read
.specs/changes/<slug>/artifacts (brief.md, requirements.md, design.md, tasks.md) as context for any task unless:- You are explicitly in a spec-driven workflow for that specific
<slug>, OR - The user explicitly references or asks about that specific spec artifact
- Treat spec artifacts as ephemeral snapshots of past intent — they do not reflect current codebase state and must never be used as implementation reference outside their own spec-driven flow.
- You are explicitly in a spec-driven workflow for that specific
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.
- 5d ago First seen · 112 lines · 1,263 tokens per session scan A b9b3f4a22aa1
spec-driven-steroids AGENTS.md is an instructions file published in the GitHub repository lindoelio/spec-driven-steroids (54 stars, last pushed 26d ago), licensed MIT. It adds 1,263 tokens to every session, about $0.0063 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 2026-08-30.
Other instructions, from other repositories
sdd-pilot AGENTS.md
AGENTS.md instructions for attilaszasz/sdd-pilot, covering sdd pilot — agent context, lifecycle, runtime preflight, phase gates and core conventions.
sdd-pilot sddp-bootstrap.instructions.md
Instructions for attilaszasz/sdd-pilot: These are project-level bootstrap documents. Edit each via its owning skill.
sdd-pilot sddp-governance.instructions.md
Instructions for attilaszasz/sdd-pilot, a project described as: Replace chaotic AI code generation with a disciplined, spec-driven workflow. SDD Pilot enforces structured development phases and quality gates, leveraging AI agents to conduct online research for best practices and plan your architecture before a single…
sdd-pilot sddp-adrs.instructions.md
Instructions for attilaszasz/sdd-pilot: ADRs under specs/adrs/ follow the MADR contract in .github/skills/adr-authoring/SKILL.md.
sdd-pilot sddp-specs.instructions.md
Instructions for attilaszasz/sdd-pilot: When editing feature-artifact files inside specs/ /, follow the canonical preservation, format, and section rules in .github/skills/artifact-conventions/SKILL.md.
sdd-pilot CLAUDE.md
Claude Code instructions for attilaszasz/sdd-pilot: Follow the project instructions defined in project-instructions.md.