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.
git clone --depth 1 https://github.com/simonrowland/goal-flightWrote 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/simonrowland/goal-flight/build-corpus)<a href="https://agentmods.dev/commands/simonrowland/goal-flight/build-corpus"><img src="https://agentmods.dev/badge/commands/simonrowland/goal-flight/build-corpus.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 | $0.00023 | $0.01266 |
| Opus 5 | $0.00012 | $0.00633 |
| Sonnet 5 | $0.00005 | $0.00253 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade A, and why
build-corpus 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 yesterday.
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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
build-corpus [--slice ] [--next-wave []] [--all] [--rebuild]
Build, extend, or rebuild the docs-private/rag/ corpus after init step 9 has
created docs-private/rag/ORIENTATION.md. Same 4-pass pipeline; invocation
outside init.
Modes
| Args | Mode | Behaviour |
|---|---|---|
(none) or --next-wave |
Next-wave extension — read most recent final-assessment's "Next-wave priorities" list from RESUME-NOTES; build those slices | |
--next-wave <N> |
Cap at top N priority slices | |
--slice <name> |
Build or rebuild one named slice (e.g. --slice binding-spec/electrolysis-step.md) |
|
--all |
Full rebuild — re-run all slices from scratch | |
--rebuild |
Re-run every existing slice but don't add new ones |
4-pass pipeline
Schema reference: templates/rag-corpus-schema.md.tpl (directory shape + per-slice word budgets + verified-at: <commit-SHA> frontmatter convention). Orientation reference: templates/worker-orientation.md writes the canonical docs-private/rag/ORIENTATION.md brief.
Pass 0 — orientation refresh (orchestrator inline). Rebuild
docs-private/rag/ORIENTATION.md from templates/worker-orientation.md and the
project's north-star, architecture, SRS, and project-map docs before dispatching
slice builders. Keep it pointer-heavy and scoped: orientation only, never scope
expansion.
Pass 1 — slice builders (parallel workers via the orchestrator's host delegate mechanism). For each target slice, dispatch a builder through a ready adapter. Brief: read the slice's source materials (the orchestrator names the project docs each slice distills — north star, architecture, SRS, protocol/spec files — when it picks the slice), produce a slice file at the schema-defined path with frontmatter verified-at: <current-HEAD-SHA>. Builder OVERWRITES for --all / --rebuild; WRITES new for --slice / --next-wave. No prompt-template file needed — the slice schema + source-list + verification-first principle are sufficient brief.
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.
- yesterday Changed · +2 lines · +14 tokens per session 5164c50f62fc
- 7d ago First seen · 61 lines · 9 tokens per session scan A 0888a4267bf5
build-corpus is a command published in the GitHub repository simonrowland/goal-flight (20 stars, last pushed today), licensed MIT. It adds 23 tokens to every session and 1,266 once invoked, about $0.0001 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 commands, from other repositories
retrieval
Search the user's Ryu memory and knowledge Spaces (RAG).
mine
Quickly capture relevant project context into Memento memory.
search
Search your memories using Memento hybrid retrieval.
pm-crystallize
Promote a project-local lesson to /.great-pm/decisions.md (cross-project memory) when it has 3+ hits with high confidence. Surfaces candidates as PROPOSALS — never auto-promotes; human approval required.
new-rag
Scaffold a new RAG (Retrieval-Augmented Generation) pipeline with best practices.
checklist
Generate a custom checklist for the current feature based on user requirements.