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/dustinvk/wherefore/seedgit clone --depth 1 https://github.com/DustinVK/whereforeWhat 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 | $0.00015 | $0.02229 |
| Opus 5 | $0.00008 | $0.01115 |
| Sonnet 5 | $0.00003 | $0.00446 |
| Haiku 4.5 | $0.00002 | $0.00223 |
Grade A, and why
seed 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are bootstrapping the controlled vocabulary for this project's wherefore log,
the two-facet wherefore/topics.md used by the capture and ask skills. Read
the codebase, propose a draft vocabulary, and, only after the user confirms,
write it.
Scope: if $ARGUMENTS names a path, focus your inspection there; otherwise inspect
the whole repo from its root.
1. Gather signals (read-only)
Infer the two facets from real structure, not guesses:
Areas: feature slices / product domains (WHAT):
- Top-level source layout and module/package names; feature folders and bounded
contexts are the strongest signal. List the tree first (e.g.
find . -maxdepth 2 -type d, orgit ls-files | head -200for tracked structure). - Route / endpoint / controller / handler names, and the domain nouns in the
README and any
docs/. - Group related code into coarse, stable buckets: one area per product capability
(
checkout,billing,catalog), NOT one per file or sub-feature.
Topics: cross-cutting technical concerns (HOW):
- Dependency manifests and lockfiles (
package.json,go.mod,requirements.txt,pom.xml,Gemfile,Cargo.toml, ...), Dockerfiles, IaC, and anymigrations/directory. These reveal the stack: the database, auth approach, queues, etc. - Recurring engineering concerns visible in the tree (
auth,data-model,performance,security,api-design,infra,frontend).
Keep each list to roughly 6-12 entries. Resist sprawl; coarse and reusable beats exhaustive. Use lowercase, hyphenated tags.
2. Propose (do NOT write yet)
Present the proposal in the two-section format below, and for EACH tag add a short (3-8 word) justification pointing at what in the codebase suggested it, so the user can sanity-check:
## Areas: feature slices / product domains (WHAT)
- checkout # src/checkout/, /api/checkout routes
- billing # src/billing/, Stripe client
## Topics: cross-cutting technical concerns (HOW)
- postgres # migrations/, pgx in go.mod
- auth # internal/auth/, JWT middleware
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 First seen · 166 lines · 15 tokens per session scan A dedc27a19e82
seed is a command published in the GitHub repository DustinVK/wherefore (1 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 2,229 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 2026-08-31.
Other commands, from other repositories
adr-backfill
Audit code, documentation, and history for potential architecture decisions that were never recorded, then return a deduplicated evidence report. Read-only.
adr-draft
Draft one new ADR from a current decision or a selected backfill handoff. Writes a single new record, as proposed.
adr-check
Check the current change, or a plan, against the decisions that govern it and report a verdict per decision. Read-only.
adr-queue
Show the review queue — every decision still proposed, with its SLA state — so open questions are visible before they are planned around. Read-only.
release-adr-kit
You are running the adr-kit release for version $ARGUMENTS (if empty, ask which version to release).
adr-context
Load the architecture decisions that govern the paths you are about to change, before planning against them. Read-only.