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 scott-fryxell/brayness --skill memorygit clone --depth 1 https://github.com/scott-fryxell/braynessWrote 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/scott-fryxell/brayness/memory)<a href="https://agentmods.dev/skills/scott-fryxell/brayness/memory"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/memory/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/scott-fryxell/brayness/memory"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/memory.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 | $0.00117 | $0.00617 |
| Opus 5.5 | $0.00047 | $0.00247 |
| Sonnet 5.5 | $0.00023 | $0.00123 |
| Haiku 4.5 | $0.00012 | $0.00062 |
Grade A, and why
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 28d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Learnings are written to AGENTS.local.md (or
AGENTS.md for rules everyone must see). AGENTS.local.md is loaded into the
system prompt every session by the agents-local extension, so a lesson
written there is guaranteed to be in context next session - no on-demand
recall needed. The same extension syncs the work/ project table in that
file from disk each session; edit descriptions there, not the row list. This separates it from the vault (your knowledge) and
from AGENTS.md (standing rules).
Only cross-cutting lessons learned from experience belong here. Standing
policies go in AGENTS.md; fix-specific trivia stays with the project. Keep AGENTS.local.md small - every line costs tokens
in every session.
Write after a correction or outcome
On a user correction, a repeated failure, or a notable outcome, append a dated
bullet under a ## Learnings section in AGENTS.local.md:
## Learnings
- YYYY-MM-DD: [the one reproducible lesson / hint]
Keep every entry to 5-7 words - one hint, no reasoning. If the lesson should
guide every agent, put it in AGENTS.md instead - other harnesses read
that, not AGENTS.local.md.
Read before you act
AGENTS.local.md is already in your system prompt every session - check it
before acting. If a past entry says a given approach failed, say so and take
the other route.
Critical refinement loop
On a user correction or a repeated failure, work the loop:
- Name the exact correction/failure.
- Gather evidence: the user's words, the failing command/output, the file path.
- Decide whether the fault is in a skill/process or was a one-off mistake.
- If it points at a skill defect, propose the change as a diff to that skill's
SKILL.md(in chat, or a file underplans/for bigger rewrites) and wait for a human to approve before editing the production skill. - Append the learning to
AGENTS.local.mdLearnings regardless.
The producer never grades its own homework: when reviewing your own work, reason from evidence and state what is wrong plainly.
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.
- 28d ago Changed 66b7e3c85825
- 1mo ago First seen · 53 lines · 117 tokens per session scan A e3be91cb1d94
memory is a skill published in the GitHub repository scott-fryxell/brayness (125 stars, last pushed 29d ago), licensed MIT. It adds 117 tokens to every session and 617 once invoked, about $0.0005 per session on Opus 5.5. 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 skills, from other repositories
knowledge-ingest
Ingest documents, articles, conversations, or supplied text into Knowledge with retained originals, sourced claims, entity updates, timelines, and cross-links; also learn durable lessons from a set of conversations, transcripts, or past sessions (/learn). Routes meetings to knowledge-meeting-ingest and short thoughts…
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…