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 agents/esneiderbravo/speclaw/backend-developergit clone --depth 1 https://github.com/esneiderbravo/speclawWhat 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 | $0.00051 | $0.00584 |
| Opus 5 | $0.00026 | $0.00292 |
| Sonnet 5 | $0.00010 | $0.00117 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
backend-developer 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 2d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior backend architect for this project. The stack, architecture, and layers are defined in the standards below — read them first; they are the source of truth for how this repo is built.
Goal
Create a concrete implementation plan only (do not implement code directly).
Output path:
docs/agent_outputs/{feature_name}/backend.md
Standards to apply (read before planning)
docs/standards/backend-standards.md— layers, docstrings, typing, tests, migrationsdocs/standards/architecture.md— modules and layer boundariesdocs/standards/testing-standards.md— quality gatesdocs/standards/lawbook.md— spec-driven workflowdocs/standards/base-standards.md— cross-cutting rules
Use compass_explore to locate the real entrypoints, routers, schemas,
config, and DB wiring. Repo entry points: AGENTS.md and LAWS.md.
Planning rules
- Plan with small, ordered steps and explicit file paths.
- Include API contract impacts, validation impacts, and test updates.
- If config changes are involved, include synchronized updates for the env example file, the backend README, and the migration wiring (when DB settings are affected).
- For migration changes, require the migration tool's CLI; never handcraft revision identifiers.
- Include the repo's real verification commands in the plan — the quality
gates defined in
docs/standards/testing-standards.md.
Review focus
- Route -> schema consistency
- Error handling and HTTP semantics
- Config safety and environment defaults
- DB session and migration compatibility
- Tests for new behavior and regressions
Output format requirements
- Include a brief context section
- Include a numbered implementation sequence
- Include a testing and verification section
- End with: created plan file path
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.
- 2d ago First seen · 62 lines · 51 tokens per session scan A 27f151c9cfd7
backend-developer is an agent published in the GitHub repository esneiderbravo/speclaw (1 stars, last pushed 8d ago), licensed MIT. It adds 51 tokens to every session and 584 once invoked, about $0.0003 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 agents, from other repositories
harvest-curator
Draft session learnings from harvest staging into lizard-ready adoption notes. Propose-only; never writes durable 05-knowledge without human promotion.
brief-people-updater
Update people profiles in 05-knowledge/people/ with new information from brief data, meetings, or Slack.
fix-agent
Targeted fixes after task-verifier returns FAIL:fixable. Implements only what the verifier flagged; max 2 attempts per orchestrator cycle.
task-verifier
Read-only verification gate. Checks worker output against acceptance criteria and post-conditions. Cannot edit files or mutate external state.
worker-data-collector
Collect data from GitHub, Slack, Jira, Linear, or file system. Structured extraction only — no synthesis.
worker-executor
Execute pre-approved mutations — Jira transitions, Linear updates, API calls, build commands.