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 commands/starmynd-org/infinite-brain-harness/syncgit clone --depth 1 https://github.com/starmynd-org/infinite-brain-harnessWrote 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/commands/starmynd-org/infinite-brain-harness/sync)<a href="https://agentmods.dev/commands/starmynd-org/infinite-brain-harness/sync"><img src="https://agentmods.dev/badge/commands/starmynd-org/infinite-brain-harness/sync.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 | $0.00000 | $0.01207 |
| Opus 5 | $0.00000 | $0.00603 |
| Sonnet 5 | $0.00000 | $0.00241 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sync: back up my work and get the latest
Sync every brain mounted under internal/. Convention: a folder named individual-* is an individual brain (push
freely); every other brain mounted under internal/ is a shared brain (content is free to push, core changes go to
a review branch). Backend is plain git (GitHub by default). Use GIT_TERMINAL_PROMPT=0 so git fails fast,
and report any auth error as one friendly line, never as raw git output.
Step 0: Preflight
If internal/ has no mounted brains, tell the person to run /start first and stop. Ensure each brain has a git
identity set (from /start); set it if empty.
Step 1: Individual brains (free)
For each internal/individual-*:
git -C "$b" add -A
git -C "$b" commit -m "<name>: <short summary>" # skip if nothing to commit
GIT_TERMINAL_PROMPT=0 git -C "$b" pull --rebase origin HEAD
GIT_TERMINAL_PROMPT=0 git -C "$b" push origin HEAD
On an auth error, say the backup did not go through (fix git access) and continue.
Step 2: Shared brains (governed)
For each shared brain (every brain mounted under internal/ not named individual-*):
- Pull the latest release first:
git -C "$b" fetch originthen merge the shared branch (origin/mainor the brain's default). On a merge conflict on shared canon, do not force it: tell the person to ask the brain's maintainer, and include the conflicting file names. - Classify local changes (
git -C "$b" status --porcelain):- content (free): paths under
outputs/orsessions/. - core (needs review): anything else, especially
entities/,knowledge/,_system/,workflows/,automations/,tools/,bin/,docs/,data/, and root orientation.
- content (free): paths under
- If only content changed: commit and push to the shared branch.
- If any core changed: do NOT push to the shared branch. Park the whole changeset on a review branch
so nothing core lands unreviewed:
Then tell the person it changes the shared brain, so it is on a review branch; ask the brain's maintainer to review and merge. The working copy is back on the shared branch and clean.git -C "$b" switch -c "proposal/<name>-<topic>" git -C "$b" add -A && git -C "$b" commit -m "<name> proposal: <what and why>" GIT_TERMINAL_PROMPT=0 git -C "$b" push -u origin "proposal/<name>-<topic>" git -C "$b" switch <shared-branch>
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 · 87 lines · 0 tokens per session scan A 16f52136f2f9
sync is a command published in the GitHub repository starmynd-org/infinite-brain-harness (23 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,207 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.