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 skills add ZenSystemAI/Zengram --skill bashgit clone --depth 1 https://github.com/ZenSystemAI/ZengramWrote 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/zensystemai/zengram/bash)<a href="https://agentmods.dev/skills/zensystemai/zengram/bash"><img src="https://agentmods.dev/badge/skills/zensystemai/zengram/bash/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/zensystemai/zengram/bash"><img src="https://agentmods.dev/badge/skills/zensystemai/zengram/bash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00958 |
| Opus 5.5 | $0.00000 | $0.00383 |
| Sonnet 5.5 | $0.00000 | $0.00192 |
| Haiku 4.5 | $0.00000 | $0.00096 |
Grade A, and why
bash scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> This adapter covers 6 of the 13 Zengram tools (store, search, briefing, query, stats, consolidate). The remaining 7 (entities, delete, update, export, import, reflect, research) are reachable directly over REST with `c How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Shared Brain — Bash CLI Adapter
Command-line interface for the Zengram system. Use this to store, search, and retrieve shared memories from any terminal-based agent or script.
This adapter covers 6 of the 13 Zengram tools (store, search, briefing, query, stats, consolidate). The remaining 7 (entities, delete, update, export, import, reflect, research) are reachable directly over REST with
curl— seeexamples/curl-demo.sh. Prefer curl over adding new subcommands here.
Requirements
curlandjqmust be installed- Set
BRAIN_API_KEYas an environment variable, or place it in$HOME/.config/zengram/.env
Configuration
| Variable | Default | Description |
|---|---|---|
BRAIN_API_URL |
http://localhost:8084 |
API server URL |
BRAIN_AGENT_NAME |
my-agent |
Persisted as every write's source_agent AND used as the briefing self-exclusion filter. Set a stable, unique name per agent — briefings, filters, and cross-agent corroboration key off it. |
BRAIN_API_KEY |
(required) | API key for authentication |
BRAIN_ENV_FILE |
$HOME/.config/zengram/.env |
Path to env file |
Commands
Store a memory
./brain.sh store \
--type "fact" \
--content "acme-corp prefers formal tone in all communications" \
--client_id "acme-corp" \
--category "semantic" \
--importance "high"
Parameters:
--type(required):event|fact|decision|status--content(required): The memory content--client_id: Client/project slug orglobal(default:global)--category:semantic|episodic|procedural(default:episodic)--importance:critical|high|medium|low(default:medium)--key: Unique key for facts (enables upsert — new facts with the same key supersede old ones)--subject: Subject for status updates (enables upsert by subject)--status_value: Current status string (for status type)
Semantic search
./brain.sh search \
--query "client tone preferences" \
--client_id "acme-corp" \
--limit 5
What ships with it
1 file 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.
- 1mo ago First seen · 100 lines · 0 tokens per session scan A fbf95a43d2b9
bash is a skill published in the GitHub repository ZenSystemAI/Zengram (64 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 958 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.