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 mycelium-hq/ai-brain-starter --skill ingest-githubgit clone --depth 1 https://github.com/mycelium-hq/ai-brain-starterWrote 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/mycelium-hq/ai-brain-starter/ingest-github)<a href="https://agentmods.dev/skills/mycelium-hq/ai-brain-starter/ingest-github"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/ingest-github/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/mycelium-hq/ai-brain-starter/ingest-github"><img src="https://agentmods.dev/badge/skills/mycelium-hq/ai-brain-starter/ingest-github.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00116 | $0.01523 |
| Opus 5.5 | $0.00046 | $0.00609 |
| Sonnet 5.5 | $0.00023 | $0.00305 |
| Haiku 4.5 | $0.00012 | $0.00152 |
Grade A, and why
ingest-github 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 1mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ingest-github: GitHub-to-vault connector
{SKILL_DIR}= this skill's own folder (locally: the directory this SKILL.md lives in; a served brain substitutes the real absolute path before you read this). If a path does not resolve, name the missing file and stop — never guess another location.
Ingests recent GitHub repository activity into the vault as markdown the graphify pipeline can read and the rest of the AI Brain Starter substrate (decision log, session-close cascade, hooks) can act on.
This is the second connector in the ingest-* pattern. Adding the next external source means writing a new normalizer, not a new architecture.
When to use
- User says
/ingest-github <owner/repo>(with or without--days N) - User asks to capture, sync, ingest, or pull a GitHub repository into the vault
- User mentions wanting recent PRs, issues, or commits available to the knowledge graph
Do NOT use for:
- Opening pull requests or creating issues (use the GitHub MCP write tools or
ghCLI directly) - One-off PR diff reads (use
gh pr viewor the GitHub MCP) - Non-GitHub sources (Slack, Notion, email get their own connectors)
How it works
- Parse the
<owner>/<repo>argument, normalize to a slug (owner-repo) - Fetch merged PRs from the last N days (default 7) via the GitHub MCP
list_pull_requeststool (state=closed, filter to merged) - Fetch issues from the last N days via
list_issues(any state, since the date window) - Fetch commits from the last N days on the default branch via
list_commits - For each PR with a body, optionally pull review comments and inline conversation
- Normalize all items chronologically into one markdown body, grouped by item type
- Write to
External Inputs/GitHub/<owner-repo>/<YYYY-MM-DD>.md - Print summary: file path, PR count, issue count, commit count
Voice rules
- No em dashes (use commas, colons, periods, parentheses)
- No exclamation marks
- Direct, no fluff
- Author logins quoted verbatim (the GitHub login, not the display name)
- Body excerpts truncated at 800 characters per item to keep the vault file readable
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.
- 1mo ago First seen · 105 lines · 116 tokens per session scan A c30a189ad05a
ingest-github is a skill published in the GitHub repository mycelium-hq/ai-brain-starter (47 stars, last pushed 3d ago), licensed MIT. It adds 116 tokens to every session and 1,523 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 2026-08-31.
Other skills, from other repositories
nightly
Canonical seven-leg nightly close-parity protocol. Eleven independently evidenced checkpoints cover synthesis, reconciliation, context hygiene, sweeps, heat, digest, runtime health, cognitive state, ledger capture/review, and vault sync.
Promote
Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back…
Stuck
Walk the 6-rung escalation ladder before declaring stuck or asking the principal. Most "stuck" is actually "haven't tried the next approach." Stopping is the last resort, not the first response.
open
Boot the session, load context from the vault, and surface what matters.
start
The day-one first-run flow and the everyday home screen. On first launch, greet, run setup, then carry the operator into a real first win. On return, give a short briefing and action menu.
caddy-mute
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.