Borrowing it
Nothing to install: this file belongs to gabrielzucco/cerebro-inevita. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gabrielzucco/cerebro-inevita/main/.agents/skills/company-brain-sprint/SKILL.mdgit clone --depth 1 https://github.com/gabrielzucco/cerebro-inevitaWrote 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/gabrielzucco/cerebro-inevita/company-brain-sprint)<a href="https://agentmods.dev/skills/gabrielzucco/cerebro-inevita/company-brain-sprint"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/company-brain-sprint/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/gabrielzucco/cerebro-inevita/company-brain-sprint"><img src="https://agentmods.dev/badge/skills/gabrielzucco/cerebro-inevita/company-brain-sprint.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 | $0.00000 | $0.01820 |
| Opus 5.5 | $0.00000 | $0.00728 |
| Sonnet 5.5 | $0.00000 | $0.00364 |
| Haiku 4.5 | $0.00000 | $0.00182 |
Grade A, and why
company-brain-sprint 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 20d 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Company Brain Sprint
The folder is the Company Brain. Manus, Codex, Claude, Gemini or another file-based AI is only the current operator. Work directly in the local folder and keep all durable context there.
Deliver this chain:
orientation → source register → evidence → observed slice → CONFIGURATION → use → correction → reuse
Read .cerebro/layout.json, references/output-contract.md and
protocol/system-contract.schema.json when that path exists before writing. Do not claim to map the
whole company in one activation.
Non-negotiables
- Use only files the owner explicitly placed in or authorized for this brain.
- Inspect the smallest useful sample. Do not browse or connect external systems unless asked.
- Raw evidence remains raw and traceable; never paste the full corpus into derived context.
- Self-report is
[DECLARED]; inspected records are[OBSERVED]; reasoning is[INFERRED]until the owner confirms it. Missing facts areunknown, never plausible filler. - Keep map state separate from evidence coverage. V0→V3 measures evidence; T0→T4 measures Base Brain activation. Never promote one from the other.
- Registering a source records its location, purpose, authority and access state. It is not a connection, ingestion, index or synchronization.
- Require owner confirmation before persisting the map, approving the activation use or turning a correction into a reusable rule.
- Defer write/action integrations and automation until one manual run has proven useful.
- Ask one compact question at a time when interaction is available. Never expose run IDs, telemetry, internal milestones or implementation jargon during onboarding.
1. Establish ownership and recover the job
Confirm that the current working directory is the folder the owner wants to keep as their Company Brain. Do not ask for email. First recover a concrete operation from the current request, handoff or authorized files. If it is already clear, state what you understood and proceed.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 20d ago Changed · +2 lines 527585ba3c6d
- 1mo ago First seen · 150 lines · 0 tokens per session scan A 9cf88fb3104b
company-brain-sprint is a skill published in the GitHub repository gabrielzucco/cerebro-inevita (7 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,820 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 skills, from other repositories
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
agent-memory-discipline
Rules for when an agent should recall from long-term memory before acting and when it should save decisions, corrections and failures afterwards. Works with any memory backend.
ai-agents-architect
Expert in designing and building autonomous AI agents. Masters tool use, memory systems, planning strategies, and multi-agent orchestration.
session-compact
AI DevKit · Compact a historical AI coding session with Jev when context is long, work is handed off or resumed, or durable continuation facts and memory candidates need extraction.
context-management-context-save
Capture and serialize project state, architectural decisions, and working context. Use when preserving knowledge for later sessions, handoffs, or searchable context retrieval.
handoff
Prepare a clean cross-session handoff so the next agent can pick up where you left off. Saves a focused Work Checkpoint with gsdcheckpointsave and ensures summary artifacts are current. Use when asked to "hand off", "prepare handoff", "pause work", "bookmark this", "I'll come back to this later", before running out of…