review-seams

A read-only code-review command checks the places where data crosses boundaries, such as saved files, events, processes, or pause-and-resume flows, for missing or inconsistent types.

In plain words
What is it for?
Use it to inspect changed code at serialization, persistence, event, language, process, and runtime handoffs.
Why use it?
It helps find cases where data is misread, fields disappear, validators are skipped, or duplicate definitions drift apart.

Command

Install

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.

agentmods
npx agentmods add commands/coleam00/archon/review-seams
Clone the repo
git clone --depth 1 https://github.com/coleam00/Archon
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,869 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01869
Opus 5 $0.00000 $0.00934
Sonnet 5 $0.00000 $0.00374
Haiku 4.5 $0.00000 $0.00187

Measured yesterday against content hash edecc7b36122, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-seams 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.

.archon/workflows/sdlc/review/commands/review-seams.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Seam Review — Missing Types at Boundaries

Hunt one defect: a type is missing at a seam, and something downstream pays for it — a parser that mis-reads, a hand-synced copy of a set, type, or table whose owner it could import or derive from, a second route that skips the validator, a value that silently loses fields across a re-entry. Read-only: never modify files, commit, or post anywhere.

Read $ARTIFACTS_DIR/review/scope.md first, and the project's architecture.md if it has one. Anchor the review on the accepted work order's stated invariants, and scale depth to what the change can destroy: irreversible or destructive paths, lifecycle ownership, persisted contracts and schemas, credentials and auth boundaries, integration boundaries, and concurrency over shared state each get an explicit attempt to refute the invariant they rest on; a prose-only change gets the minimum. In light mode, verify prior seam findings first, then examine only the delta.

A seam is where a value crosses to something that must interpret it: serialization, process/language boundaries, events, persisted formats, pause/resume re-entry, load-time→run-time handoffs. A plain function call is not a seam.

The defect is never in the diff

The added code is usually correct in isolation; what is wrong is the counterpart it now disagrees with — which is not in the diff. For every site the change touches, leave the diff and find its counterparts:

  • Edits one member of an enumerated set (a field list, a walker, a per-variant dispatch) → find every other member; one of them likely needed the same edit.
  • Adds a syntax form, key, or shorthand → find every consumer of that syntax; the route that doesn't know the new form admits it unchecked.
  • Adds a field on a resume/retry/rehydrate path → diff the field set against the primary construction path.
  • Adds a variant to a union → find every switch over it; look for the silent default.
  • Verifies a counterpart that dispatches on a discriminant (a kind, surface, or spec-table lookup) → open the discriminant's defining table. The table owns the set; changed code that re-enumerates its members by hand disagrees with the owner in structure even while the values agree.
  • Adds a validation → count every route in to what it guards; one validator and three ways in is two holes.
  • Writes a value something else reads → read the reader; a formatter/parser pair written at different times and nowhere checked to be inverses.

Read the full file on GitHub · 53 lines

Changes

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.

  1. yesterday First seen · 53 lines · 0 tokens per session scan A edecc7b36122

Subscribe to this mod's changes

review-seams is a command published in the GitHub repository coleam00/Archon (23,313 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,869 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.