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/sandeep84397/agent-brain/project_context_templategit clone --depth 1 https://github.com/sandeep84397/agent-brainWhat 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 | $0.00000 | $0.01046 |
| Opus 5 | $0.00000 | $0.00523 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
PROJECT_CONTEXT_TEMPLATE 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Context — Template
Copy this file into your repo as CLAUDE.md (or merge into your existing one) so every agent that enters the repo can resolve the same identity, paths, team, and brain conventions.
Bundled agent templates (backend-engineer.md, principal-engineer.md, etc.) read this on every task — if any required section is missing, the agent should ask the user before proceeding.
Repo Identity
- Name:
<repo-name-as-registered-in-brain-config>(must match the key in~/.agent-brain/config.jsonrepos) - Brain repo tag: the same name — passed as
repo=<name>to every brain tool call - Root path:
/absolute/path/to/this/repo - Stack: e.g.
Python 3.12 + FastAPI,Kotlin + Ktor,TypeScript + Next.js - Owner: the lead engineer's name
Paths
Tell agents where the canonical artifacts live. Use absolute paths or paths relative to the repo root.
- PRDs:
docs/prds/ - Architecture notes:
docs/architecture/ - Active blockers:
docs/BLOCKERS.md - Sprint plan:
docs/sprints/current.md - Test plans:
docs/test-plans/
Team
Canonical agent names and roles for this repo. Names should match ~/.agent-brain/config.json team entries (or the per-repo teams_per_repo override). Agents use these to address each other in heartbeat(... talking_to="...").
| Role | Name | Notes |
|---|---|---|
| Principal Engineer | marcus |
architecture gate |
| Product Owner | maya |
PRD owner |
| Backend Engineer | arjun |
|
| Frontend Engineer | priya |
|
| QA Engineer | rahul |
|
| Project Manager | vikram |
Brain Conventions
- Repo tag: every
log_decision/pre_checkcall must userepo="<name>"from above. - Area prefix: group decisions by area, e.g.
auth,feed,schema,ui. Use the same area name across decisions for the same subsystem soquery_decisions(area=...)finds them. - Heartbeat repo: when this project ships per-repo office state (see config
teams_per_repo), passrepo="<name>"toheartbeat()so the agent doesn't appear in other repos' dashboards. - Outcome owners: PRs reviewed by
marcus(architecture) →outcome_by="marcus". Test failures from CI →outcome_by="ci".
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 · 65 lines · 0 tokens per session scan A eac9b688f0c7
PROJECT_CONTEXT_TEMPLATE is an agent published in the GitHub repository sandeep84397/agent-brain (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,046 tokens. 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
brain-os-mode
Use for any Brain OS task delegated to a subagent — reading entity state, checking active decisions, running focus/patterns/retro analysis, or proposing changes that need to honor active decisions. Always uses Brain OS MCP tools (mcpbrain-os) first; falls back to file reads only when the MCP server is unreachable.…
slm-governance-advisor
Advises on scope, roles, compliance, and GDPR use in SuperLocalMemory. Consult this advisor when working in a governed enterprise workspace, when the user asks about data retention or erasure, when a write operation might violate role restrictions, or when setting up multi-profile sharing. Never bypasses governance…
slm-memory-advisor
Advises the main agent on using SuperLocalMemory well — when to call sessioninit, remember, recall, and search; how to phrase queries; and how to keep memory clean. Delegate here for any "should I save/recall this?" decision or when memory results look wrong.
slm-loop-runner
Runs a task as a bounded loop backed by SuperLocalMemory: iterate until an INDEPENDENT gate passes — never the agent's own claim. Delegate here when a task has a checkable acceptance condition (a test suite, a JSON schema, a linter, a reconciliation rule, a security scan) and you want gate-verified completion with an…
agent-design-patterns
LLM 에이전트 설계 패턴 레퍼런스. Anthropic "Building Effective Agents" 5가지 패턴 + 실전 적용 기준. 워크플로우 vs 에이전트 구분, 패턴별 트레이드오프, 프로덕션 배포 체크리스트. 2025 기준.
mcp-advanced-patterns
MCP(Model Context Protocol) 심화 패턴 레퍼런스. 2025 Anthropic 권고 사항 기준. HTTP Streamable Transport, 도구 설계 원칙, 컨텍스트 효율화, 엔터프라이즈 인증, 보안 고려사항. 실제 Claude Code + OpenAkashic MCP 운영 경험 기반.