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 skills add wedabro/bro-skills --skill speckit.backendgit clone --depth 1 https://github.com/wedabro/bro-skillsWrote 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/skills/wedabro/bro-skills/speckit.backend)<a href="https://agentmods.dev/skills/wedabro/bro-skills/speckit.backend"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.backend/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/skills/wedabro/bro-skills/speckit.backend"><img src="https://agentmods.dev/badge/skills/wedabro/bro-skills/speckit.backend.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 | $0.00033 | $0.02199 |
| Opus 5 | $0.00016 | $0.01099 |
| Sonnet 5 | $0.00007 | $0.00440 |
| Haiku 4.5 | $0.00003 | $0.00220 |
Grade A, and why
speckit.backend 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 10d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Build the smallest production-ready backend change that honors the feature
specification and the existing architecture. Prefer a modular monolith unless
the specification demonstrates a need for distributed complexity. Match
.agents/knowledge_base/api_standards.md, data_schema.md, and the project
constitution.
Required Inputs
.agents/specs/[feature]/spec.md,plan.md, andtasks.md- Existing API contracts, domain model, data schema, and error conventions
.agents/memory/constitution.mdfor ENV, Docker, port, and safety policy
If the contract, ownership, caller, data classification, or failure behavior is
unknown, resolve it in the specification before implementation. Use
speckit.database, speckit.security, speckit.devops, or speckit.tester
for specialized work rather than duplicating their scope.
Protocol
0. Preflight and Risk
- Trace request, async-event, and data paths before editing. Identify callers, authorization boundary, side effects, transaction owner, dependencies, and rollback or recovery behavior.
- Classify the change as read-only, reversible write, irreversible write, or externally visible contract change. For payments, identity, PII, tenant data, migrations, queues, or destructive work, state the risk and mitigation.
- Reuse the project's error, validation, configuration, logging, persistence, and dependency-injection patterns. Do not introduce a framework, vendor, or architectural pattern without a documented need.
1. Contract-First API
- Define or update the contract before handler logic: consumer, resource or operation, authorization, request/response schemas, examples, errors, pagination/filter/sort semantics, limits, and rate-limit behavior.
- Keep public changes additive when possible. Version, deprecate, and announce breaking changes; never silently change a field's meaning or error shape.
- Validate every untrusted boundary input (HTTP, webhook, queue, CLI, file, environment) with a schema. Reject invalid input early with stable, actionable client errors; normalize only after validation.
- Use a consistent error envelope. Map expected domain failures deliberately; centralize unexpected-error handling and never expose stack traces, secrets, internal IDs, or provider responses.
- Make retriable mutations idempotent when duplicate execution can charge, create, send, or otherwise cause side effects. Define idempotency-key scope, TTL, conflict response, and persisted result where applicable.
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.
- 10d ago First seen · 169 lines · 33 tokens per session scan A e1495d804157
speckit.backend is a skill published in the GitHub repository wedabro/bro-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 2,199 once invoked, about $0.0002 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 skills, from other repositories
mx-lookup-post-batch
Retrieve MX records for up to 50 domains in a single request. Results for each domain are sorted by priority ascending (lowest numeric value has the highest mail delivery priority per RFC 5321).
trivia-post-batch
Returns up to 50 trivia questions in a single request.
email-validate-post-email
Validates a single email address and returns a full breakdown of syntax validity, MX record status, disposable domain check, normalized form, and any typo suggestion.
timezone-post-batch
Look up timezone information for up to 50 locations in a single request. Each item can specify a timezone name, city, or lat/lon coordinates. Priority is timezone name > city > coordinates. Results are returned in input order.
unit-conversion-post-batch
Skill "unit-conversion-post-batch" from bobadilla-tech/requiems-api-skills, covering endpoint, batch convert units, parameters, request example and response example.
domain-info-get-{domain}
Returns DNS records and availability status for the given domain.