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 neul-labs/brat --skill brat-memorygit clone --depth 1 https://github.com/neul-labs/bratWrote 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/neul-labs/brat/brat-memory)<a href="https://agentmods.dev/skills/neul-labs/brat/brat-memory"><img src="https://agentmods.dev/badge/skills/neul-labs/brat/brat-memory.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 5.1 | $0.00021 | $0.00380 |
| Opus 5 | $0.00010 | $0.00190 |
| Sonnet 5 | $0.00004 | $0.00076 |
| Haiku 4.5 | $0.00002 | $0.00038 |
Grade A, and why
brat-memory 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 6d 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.
What it actually says
brat-memory Skill
Purpose
After task completion or failure, write structured memory notes to the zkb knowledge base for future agents.
Input Schema (JSON)
{
"session": {
"task_id": "string",
"component": "string",
"engine": "string",
"duration_ms": "number"
},
"findings": {
"discoveries": ["string (new patterns, conventions)"],
"conventions": ["string (coding conventions observed)"],
"pitfalls": ["string (things to avoid)"],
"useful_commands": ["string (commands that worked)"]
},
"outcome": {
"status": "success|failure|partial",
"reason": "string"
}
}
Output Schema (JSON)
{
"notes_created": [
{
"title": "string",
"slug": "string",
"type": "fleeting|permanent",
"tags": ["string"]
}
],
"links_created": [
{
"from": "string",
"to": "string",
"type": "reference|continuation"
}
]
}
Guardrails
- ALWAYS create at least one memory note per session
- Tag notes with
memory,component:<name>,task:<id> - Link memory notes to related architecture and product notes
- Promote
fleetingtopermanentwhen a pattern is validated - On failure, write note about what went wrong for future avoidance
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.
- 6d ago First seen · 62 lines · 0 tokens per session scan A 9706b046f5be
brat-memory is a skill published in the GitHub repository neul-labs/brat (5 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 380 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
durable-session-state
Persist plans, scope decisions, evidence, and reviewer/critic verdicts to durable files during long or multi-phase tasks so work survives context compaction, session resumes, and handoffs. Use for swarm-mode tasks, before context grows large, when recording approval gates, and when resuming after compaction or a…
visited-tracker-tools
Use visited-tracker to record file coverage, avoid duplicate work, and leave handoff notes that persist across conversations.
hive.note-taking
Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
swarm-pr-review
Run a graph-guided, tool-augmented PR review using context packing, parallel exploration, mandatory repository-agnostic risk-family coverage with dispatch scaled to diff size and risk, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive…
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.