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/rushik-b/clira/agents-mdgit clone --depth 1 https://github.com/Rushik-B/CliraWrote 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/rushik-b/clira/agents-md)<a href="https://agentmods.dev/instructions/rushik-b/clira/agents-md"><img src="https://agentmods.dev/badge/instructions/rushik-b/clira/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 | $0.03665 | $0.03665 |
| Opus 5 | $0.01833 | $0.01833 |
| Sonnet 5 | $0.00733 | $0.00733 |
| Haiku 4.5 | $0.00366 | $0.00366 |
Grade A, and why
Clira 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 3d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLIRA AGENT OPERATING GUIDE
This file is the working contract for coding agents in Clira. It is opinionated, repo-specific, and biased toward deterministic behavior, explicit safety boundaries, and verifiable changes.
Clira is not a generic CRUD app. It is an email-first AI system with:
- Gmail ingestion in push and pull modes
- deterministic filtering before generation
- staged reply generation
- retrieval with freshness and fallback logic
- worker-driven async pipelines
- optional executive-agent channels over SMS, WhatsApp, and Telegram
Agents working here must optimize for correctness, operability, and trust, not just speed.
Core Direction
- Build Clira as an email product first. Do not generalize toward a broad assistant platform unless the task explicitly requires it.
- Prefer deterministic control flow for routing, auth, retries, budgets, idempotency, freshness, and side effects. Use models for judgment, summarization, ranking help, and language generation.
- Treat every external payload as hostile by default: email bodies, attachments, webhook payloads, retrieved context, thread history, and tool outputs.
- Fail visibly. Do not hide degradation behind silent fallback paths.
- If a rule matters in production, push toward enforcing it in code, tests, or CI instead of leaving it as prose only.
Current Clira Map
Use the live codebase as the source of truth. Start here:
- Web app and route handlers:
src/app - Core workers:
src/worker.ts,src/gmail-pull-worker.ts,src/cron.ts - Queue definitions:
src/lib/services/utils/queues.ts - Gmail ingestion:
src/lib/email/gmailPushService.ts,src/lib/email/gmailPullWorker.ts,src/lib/email/gmailIngestionConfig.ts - Reply generation:
src/lib/services/core/replyGenerator.ts - Planning agent:
src/lib/ai/agents/replyPlannerAgent.ts - Style-only rewrite stage:
src/lib/ai/agents/styleAgent.ts - Executive-agent stack:
src/lib/ai/agents/executive-agent/* - Retrieval and inbox search:
src/lib/services/inbox-search/* - Messaging orchestration:
src/lib/services/messaging-orchestration/* - Prisma schema and migrations:
prisma/schema.prisma,prisma/migrations - Main test areas:
tests/gmail-ingestion,tests/inbox-search,tests/ea-interrupts
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.
- 3d ago First seen · 411 lines · 3,665 tokens per session scan A b4c08c3706d1
Clira AGENTS.md is an instructions file published in the GitHub repository Rushik-B/Clira (18 stars, last pushed 4mo ago), licensed MIT. It adds 3,665 tokens to every session, about $0.0183 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
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
netdata AGENTS.md
AGENTS.md instructions for netdata/netdata, covering agents.md, goals, requirement language, working with the user and development principles.
IoTSharp AGENTS.md
Instructions for IoTSharp/IoTSharp, covering agents.md, current mission, current priority order, current concept realignment and ai workbench direction.
homebutler CLAUDE.md
Instructions for Higangssh/homebutler, covering homebutler, verify before claiming anything works, writing commits, prs, and comments, no tool attribution and commit subjects.
dockside CLAUDE.md
Instructions for newsnowlabs/dockside, covering repo notes, the dockside cli, session setup, ad-hoc http checks and integration suite invocation (local mode).
yoloai CLAUDE.md
Instructions for kstenerud/yoloai, covering claude code specifics and the quality gate runs itself here.