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 agentmods add skills/svy04/ballast/brain-initnpx skills add svy04/ballast --skill brain-initgit clone --depth 1 https://github.com/svy04/ballastWrote 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/svy04/ballast/brain-init)<a href="https://agentmods.dev/skills/svy04/ballast/brain-init"><img src="https://agentmods.dev/badge/skills/svy04/ballast/brain-init.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 | $0.00060 | $0.00724 |
| Opus 5 | $0.00030 | $0.00362 |
| Sonnet 5 | $0.00012 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
brain-init 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 5d 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brain scaffold
Set up the ballast memory structure in the current project. Decide everything you can yourself; report what you created instead of asking questions.
Steps
- Create
memory/in the project root and copy these templates from this skill'stemplates/directory, filling<project>placeholders with the actual project name:templates/00-INDEX.md→memory/00-INDEX.mdtemplates/DECISIONS.md→memory/DECISIONS.mdtemplates/OPEN-QUESTIONS.md→memory/OPEN-QUESTIONS.mdtemplates/SESSION-LOG.md→memory/SESSION-LOG.mdtemplates/PRODUCT-TRUTH.md→memory/PRODUCT-TRUTH.md— only if the project is (or documents) a product; skip for pure-knowledge projects and say so
- Append the session-start block from
templates/CLAUDE-snippet.mdto the project'sCLAUDE.md(create the file if missing; if the block is already there, don't duplicate it). The snippet is tool-neutral — if the project also uses Codex, append the same block toAGENTS.md(seedocs/CODEX.md). - If the user keeps rules in
.claude/ballast.rules.json, leave it untouched; if they ask for a starter catalog, copyrules/ballast.rules.example.jsonfrom the plugin root to.claude/ballast.rules.jsonand tell them to prune it. - Report: files created, files skipped (and why), and the one-line habit — "decisions get recorded the moment they're confirmed."
Conventions (explain these to the user once, briefly)
- The index is the map.
00-INDEX.mdsays what lives where and the write rules. New file types get a row there first. - The ledger is append-only. See the decision-ledger skill — never edit, only supersede.
- Open questions never dissolve silently. Unresolved items are registered in
OPEN-QUESTIONS.mdand closed with a link to the decision that resolved them. The same file holds readings in force — an "ok" that could have meant anything, written down as what the user said plus what you assumed — so a non-answer never quietly becomes a decision. - The session log is cheap insurance. A few dated bullets per working session; when context resets, this is the recovery path.
- Claims carry labels; product claims carry proof. See verify-gate and proof-standard.
- The scaffold is a floor, not a ceiling. Other skills grow
memory/later — checkpoint addsCHECKPOINT.md,checkpoints/, and the single-useHANDOFF.md; verified reference material accumulates undermemory/knowledge/. Don't pre-create these; give each a row in the index when it first appears.
What ships with it
6 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.
- 5d ago First seen · 34 lines · 60 tokens per session scan A f3ca6020b229
brain-init is a skill published in the GitHub repository svy04/ballast (71 stars, last pushed 10d ago), licensed MIT. It adds 60 tokens to every session and 724 once invoked, about $0.0003 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
alive:save
The human wants to checkpoint. Or: the stash has grown heavy — 5+ items, 30+ minutes, a natural pause in the work. The squirrel doesn't decide when to save. It surfaces the need and lets the human pull the trigger. Runs the full save protocol: confirms stash, writes log, updates state, generates projections…
alive:capture-context
Use when external content arrives in the session — emails, transcripts, screenshots, documents, files, or in-session research worth keeping. Also use when there's nothing obvious to capture — the skill checks 03Inbox/ for unrouted files and enters inbox scan mode. Stores raw content, routes to bundles, extracts tasks…
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…
alive:load-context
The human mentions a walnut to work on, asks about a specific venture/experiment/project, or wants to check status — not just explicit 'load X'. Load the brief pack (3 files), resolve the people involved, check the active bundle — then surface one observation and ask what to work on. Context loads in tiers: walnut and…
alive:mine-for-context
Deep context extraction from source material. Creates reference bundles, builds extraction plans, tracks what's been extracted, and discovers new targets — people, subjects, patterns, connections. The archaeologist that turns raw sources into structured knowledge. Can be invoked by alive:session-history for targeted…
alive:my-context-graph
Render an interactive map of your world. Generates the world index from all walnut and bundle frontmatter, then produces a force-directed graph showing connections between walnuts, people, bundles, and tags. Opens in the browser.