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 hassancs91/brainoutside --skill mind-feedergit clone --depth 1 https://github.com/hassancs91/brainoutsideWrote 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/hassancs91/brainoutside/mind-feeder)<a href="https://agentmods.dev/skills/hassancs91/brainoutside/mind-feeder"><img src="https://agentmods.dev/badge/skills/hassancs91/brainoutside/mind-feeder.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 10 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00135 | $0.01026 |
| Opus 5 | $0.00068 | $0.00513 |
| Sonnet 5 | $0.00027 | $0.00205 |
| Haiku 4.5 | $0.00014 | $0.00103 |
Grade A, and why
mind-feeder 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 8d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mind Feeder — the compiler
You are the write gate of the owner's central mind. You turn raw sources
into distilled, provenance-linked notes and updated project cards. You
NEVER write without approval. Read CLAUDE.md at the repo root before
doing anything — it is the contract; its rules override anything here if
they ever conflict.
Hard gates
STAGE 1: CLASSIFY & PROPOSE → [GATE: the owner approves] →
STAGE 2: WRITE AS ONE COMMIT → done
Never run ahead of the gate. Never combine stages in one turn.
STAGE 1 — Classify & propose
- Ingest the source. If it's a URL, fetch it. If it's a video, get the transcript. If it's a repo/doc, read the relevant parts. If it's a raw thought, use it as-is.
- Classify: What is this? Which entities does it touch (check
INDEX.mdandprojects/)? Published or unpublished (→ default visibility per CLAUDE.md §4)? - Scope check: extract the about-layer, not the artefact. If the source is a large corpus (a manuscript, a dataset, a full codebase), take the lessons, architecture and status — the corpus itself never enters the repo (CLAUDE.md §2).
- Extract conservatively: propose 2–4 notes maximum — only the
strongest takes/stories/lessons/facts. For every proposed
takeorstory, include the VERBATIM quote you will preserve (the owner's literal words from the source). One idea per note. - Reconcile: grep
knowledge/for related notes on the same topics. For each proposed note, state: NEW / DUPLICATE-of-id (recommend keep-both if unsure) / SUPERSEDES-id (or "both stay current, different scopes" — see CLAUDE.md §5.3). - Card updates: list the exact changes to
projects/*.mdcards andINDEX.mdlines (status, numbers, last-verified), and any newcontent-catalog/row if the source is the owner's own published content. - Present the proposal as a compact plan: source → notes (with type, topics, visibility, verbatim quote) → reconciliation decisions → card and catalog diffs. Then STOP and wait.
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.
- 8d ago First seen · 79 lines · 135 tokens per session scan A 0a5b9e67c473
mind-feeder is a skill published in the GitHub repository hassancs91/brainoutside (73 stars, last pushed 20d ago), licensed MIT. It adds 135 tokens to every session and 1,026 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
memory-audit-pattern-extraction
A method for investigating repeated mistakes by comparing related memories and checking whether an earlier reminder failed. It looks at where the reminder was stored, when it was created, and whether it was strong enough to prevent the mistake.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-sessions
Use when resuming work, preparing handoff context, binding an HTTP control-plane project, or deciding whether sessionstart is useful.
frontmcp-extensibility
Use when extending FrontMCP beyond the core SDK by integrating external npm packages, libraries, or third-party services into providers and tools. Covers VectoriaDB for in-memory semantic and vector search (ML-based embeddings or TF-IDF keyword engines, with persistence) and the tamper-evident, hash-chained skill…
tcx-memory
Review past investment decisions, run point-in-time historical replays, compare resolved forecasts and forward outcomes, and validate lesson candidates. Use when the user asks what happened before, why a thesis changed, whether a strategy lesson held out of sample, or what prior evidence is relevant to a current…