Borrowing it
Nothing to install: this file belongs to fulminate-io/knowledge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fulminate-io/knowledge-mcp/main/.claude/skills/walk-an-architectural-surface/SKILL.mdgit clone --depth 1 https://github.com/fulminate-io/knowledge-mcpWrote 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/fulminate-io/knowledge-mcp/walk-an-architectural-surface)<a href="https://agentmods.dev/skills/fulminate-io/knowledge-mcp/walk-an-architectural-surface"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/walk-an-architectural-surface/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/fulminate-io/knowledge-mcp/walk-an-architectural-surface"><img src="https://agentmods.dev/badge/skills/fulminate-io/knowledge-mcp/walk-an-architectural-surface.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00059 | $0.00902 |
| Opus 5.5 | $0.00024 | $0.00361 |
| Sonnet 5.5 | $0.00012 | $0.00180 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
walk-an-architectural-surface 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WALK-AN-ARCHITECTURAL-SURFACE — principles expand scope to every surface they govern
The surface walk
When the user states a guiding principle ("server has no filesystem access," "client owns session state," "no back-compat shims"), enumerate EVERY code surface the principle touches BEFORE proposing a ticket — every consumer, dependency, violation, collateral impact. Scoping narrowly to the literal request is the wrong instinct: a stated principle expands scope to every surface it governs; a missed surface costs a full correction cycle downstream.
Classify each surface: VIOLATES → ticket In Scope with concrete fix language · HONORS already → no action (document only if non-obvious) · ADJACENT but separate → named in Out of Scope with rationale · UNRELATED → drop. When the surface is wide, brief a researcher for a FULL inventory — "return every site with file:line, classified" — enumeration, not summary.
Confirm-first vs owned
Owning architecture means owning the RESEARCH and SURFACING — not deciding the foundation unilaterally. Two tiers:
- CONFIRM-FIRST (user sign-off BEFORE it enters any artifact): trust/security boundaries, transport security, auth/authz model, deployment mechanism, data-isolation model, runtime/platform assumptions, any choice with broad blast radius or depending on context the user holds.
- OWNED (decide without asking): specifics — paths, names, ordering, which existing function/pattern to reuse — and any surface fully resolvable AND verifiable from research.
Before proposing ANY architecture, research what the platform already provides. Never assume greenfield. The rule-twisting tells: reading "owns architecture" as license for a solo foundational call; relabeling a foundational decision a "specific"; resolving decide-vs-confirm ambiguity in your own favor; calling a proposal "locked" before the user signed off. Ambiguous fit → CONFIRM.
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 · 73 lines · 59 tokens per session scan A 4038aa6f2da2
walk-an-architectural-surface is a skill published in the GitHub repository fulminate-io/knowledge-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 59 tokens to every session and 902 once invoked, about $0.0002 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 2026-09-04.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…