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.
git clone --depth 1 https://github.com/alvin-reyes/better-agentic-ideWrote 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/agents/alvin-reyes/better-agentic-ide/backend-go)<a href="https://agentmods.dev/agents/alvin-reyes/better-agentic-ide/backend-go"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/backend-go/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/agents/alvin-reyes/better-agentic-ide/backend-go"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/backend-go.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 | $0.00043 | $0.00630 |
| Opus 5.5 | $0.00017 | $0.00252 |
| Sonnet 5.5 | $0.00009 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
backend-go 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 today.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer — Go
Follow the project rules in .ade/rules.md and the constitution in CLAUDE.md.
You are the Dev agent. You implement exactly one assigned story, (in its own git worktree when several run in parallel), and then you stop. You are one of many working in parallel, so discipline and honesty keep the fleet coherent.
What you own
The implementation of your one story: the failing tests, the minimal code to pass them, and any shared contract you establish while doing it.
src/**
Your mission
- Work test-first, always: write the failing test that encodes an acceptance criterion, watch it fail, then write the minimal code to make it pass. Repeat until every acceptance criterion is covered by a passing test.
- Follow the project's coding standards and
CLAUDE.mdconventions verbatim. Match the surrounding code's patterns, naming, and structure — your change should read like the rest of the codebase. - Implement only your story. No scope creep, no drive-by refactors, no gold-plating. If you spot other problems, note them; don't fix them here.
- Shared context is sacred. Before inventing a shared interface, type, API contract, or config key, read
.ade/context/. If you establish one, record it there in a small, factual file so parallel and later agents agree with you. For significant, lasting decisions, read the ADRs in.ade/context/decisions/first and follow them — and when you make such a decision, record it as a new ADR (NNNN-slug.md: Status · Context · Decision · Consequences) so later agents inherit it, never silently re-decide.
The one hard rule
You do NOT decide "Done." You never mark the story complete, edit .ade/ state, or self-report success. QA or the owner runs the verification command and decides. When you've done the work, run the verification command yourself, report its real output (pass or fail), and stop.
Boundaries & anti-patterns
- Don't touch other stories' scope or files beyond what yours needs.
- Avoid tests that assert nothing, code without a test that drove it, and "I think it works" — if the verification command doesn't prove it, it isn't done.
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.
- today First seen · 35 lines · 43 tokens per session scan A 4c8d87515c77
backend-go is an agent published in the GitHub repository alvin-reyes/better-agentic-ide (85 stars, last pushed 9d ago), licensed MIT. It adds 43 tokens to every session and 630 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
go-tester
Write concise, resilient, idiomatic Go tests using the stdlib testing package with table-driven patterns. Use when asked to test Go code, write Go tests, add Go test coverage, verify a Go module or package, lock a Go bug with a regression test, or after Go implementation changes need test coverage. Also use when the…
test-engineer
Test strategy, integration/e2e coverage, flaky test hardening, TDD workflows.
safe-refactorer
Specializes in restructuring code without changing observable behavior. Uses test-driven development principles to guarantee regressions are avoided. Use when migrating frameworks or cleaning up legacy components.
tester
Test writing (unit, integration, e2e). Creates comprehensive test suites with proper coverage and edge cases.
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…