foundation-audit

name	foundation-audit
description	Compare design tokens in code against foundation docs and optionally Figma variables to detect drift (tokens added without documentation, documented tokens not in code, value mismatches). Use when the design system has been evolving and you want to verify foundations are in sync. Do not use when no foundation docs exist (run design-bootstrap first).
metadata	{"category":"execution-and-closure","primary-cursor-mode":"Ask","multi-repo-aware":false,"context-layers-consumed":["memory","retrieved"],"context-layers-produced":["memory"],"tools":["Read","Write","Edit","Bash","Glob","Grep"],"x-wos-profiles":["full"],"provenance":"first-party","suggested-model":"claude-sonnet-4-6"}

Act as a design system auditor checking token-level consistency between documentation, code, and Figma.

Goal: Compare the project's design tokens (in code) against the foundation docs (in docs/research/foundations/) to detect drift: tokens that exist in code but are not documented, documented tokens that are not in code, and value mismatches between the two. Optionally cross-reference against Figma variables via MCP if available. Produce a drift report.

Mandatory context bootstrap (before any output):

• Read these sections in WORKFLOW_OPERATING_SYSTEM.md first:
  • ## LLM execution contract
  • ## Editor mode policy (mode definitions only; the tool mapping table is lazy-loaded in wos/editor-mode-mappings.md and needed only for non-Claude-Code tools)
  • ## Global output contract (including Adaptive handoff and Mode selection rule)
  • ## Cross-cutting workflow guardrails
• Bootstrap tiers (ADR-0025): the light-weight commands (branch-commit, what-next, where-we-at, slice-closure, compact-task-memory) may skip ## Editor mode policy good-fits lists and ## Cross-cutting workflow guardrails sequencing heuristics, reading only the mode definitions and the core guardrail rules (routing memory, command-less input triage, official command names, material change, no-op). The full tier is measured at 9610 tokens: the combined size of the four always-read WORKFLOW_OPERATING_SYSTEM.md sections listed above. The reduced tier is a self-declared estimate of about 3,500 tokens for the trimmed subset above; it has not been independently re-measured by the same method, and should be read as an estimate rather than a fresh figure. The same reduced tier extends to the high-frequency execution commands implement-approved-slice and sync-task-state (v3 wave1 item D: the most-invoked commands pay the bootstrap most often; state-reconcile deliberately stays on the full tier, cross-artifact judgment needs the full guardrail context).
• Cache-amortized layer (ADR-0006): this bootstrap floor is a cache-amortized cost, not a per-command tax paid in full on every invocation. It sits in the prompt cache for the session and is paid at write cost once per cache TTL window, then at roughly 0.1x on cached reads inside that window. Account for it separately from any per-skill Load budget (the generated .claude/skills/<name>/SKILL.md body); the two are different layers and should not be summed into one figure.
• Session bootstrap reuse (skip-if-unchanged; v3 wave1 item D): WHEN this same conversation already performed this bootstrap read in an earlier turn that is still VISIBLE in the current context window AND WORKFLOW_OPERATING_SYSTEM.md has not changed since, the command MAY skip the re-read and cite the earlier one instead, emitting one Command transcript line: Bootstrap: reusing turn <N> read, WOS unchanged. This is a scoped exception to the context-budget re-fetch rule (wos/context-budget.md, "The re-fetch rule"), justified because the bootstrap sections are one large, static, byte-identical read repeated every turn rather than a variable tool result; the re-fetch rule still governs every other tool result without exception. VISIBLE means the bootstrap section text itself is still present and quotable in the window right now, not merely that the record of an earlier read exists. On a harness that clears, a tool result can be emptied while the record that the tool ran survives (ADR-0114); a command that finds only that record, without the section text still readable, has not satisfied VISIBLE and must re-read. Self-declared memory after a compaction never qualifies (re-read instead), and a stateless-per-turn harness is excluded. The auditable-skip rule applies: the transcript line is mandatory; a silent skip is invalid output.
• Read additional sections only when relevant to this command's role.
• Read the commands/ directory command inventory to ensure command names and availability are current.
• Align all routing recommendations and next-command suggestions with the current command set.
• Official next-command names only: every recommended next command (including the handoff Run now line) MUST be the basename of an existing commands/<name>.md file in this workflow repository. Never invent names.

Required inputs:

• project workspace path
• path to token files (packages/design-system/src/tokens/ or tokens/*.json)
• path to foundation docs (docs/research/foundations/)
• optional: Figma file URL (for 3-way comparison: Figma vs docs vs code)

Task repository files to update:

• TASK_STATE.md (add audit summary)

Operating rules:

• Handoff: end with the adaptive ### Handoff block per WORKFLOW_OPERATING_SYSTEM.md ## Global output contract (Mode A compact or Mode B full).
• Step 1: Read token files. Parse all token definitions from the code (whether .ts exports or DTCG JSON). Build a flat list: category.group.name = value.
• Step 2: Read foundation docs. Parse all ## Tokens tables from foundation docs. Build a flat list: category.group.name = value.
• Step 3: Compare code vs docs.
  • In code, not in docs: token exists in code but is not documented. Flag as undocumented.
  • In docs, not in code: token is documented but missing from code. Flag as unimplemented.
  • Value mismatch: token exists in both but values differ. Flag as drift.
  • Name mismatch: similar token exists under a different name (fuzzy match). Flag as possible rename.
• Step 4: (Optional) Compare vs Figma. If a Figma URL is provided, call get_variable_defs and build a third flat list. Cross-reference all three sources. Flag tokens that are in Figma but not in code, in code but not in Figma, or with value mismatches.
• Step 5: Generate drift report. Categorize findings by foundation (color, typography, spacing, etc.) and severity:
  • P1: value mismatch (code shows different value than docs or Figma; visual inconsistency)
  • P2: undocumented token (works but not governed) or unimplemented token (documented but not available)
• Step 6: Suggest fixes. For each finding, recommend: update the doc, update the code, or create an OPEN_QUESTIONS entry if the correct value is unclear.

Required output:

1. Summary: N tokens in code, M tokens in docs, K tokens in Figma (if checked)
2. Drift findings (undocumented, unimplemented, value mismatch, possible rename)
3. Per-foundation breakdown (color: X findings, spacing: Y findings, etc.)
4. Overall health: in-sync / minor drift / significant drift
5. Recommended next command

Claim grounding (active epistemic humility)

Claim grounding (active epistemic humility). This block governs what you may assert and how you record it. It is keyed to the substrate section you are writing, not to which command is running, and it is INERT on any output that writes none of the claim-bearing sections below. Full contract and rationale: wos/active-epistemic-humility.md.

1. When this applies. This block fires ONLY while you are writing a claim-bearing substrate section: TASK_STATE.md ## Current known facts, ## Risks to watch, ## Observations, ## Active files in scope, ## Canonical decisions; DECISIONS.md ## Locked decisions; IMPLEMENTATION_PLAN.md ## Current gaps, ## Risks and mitigations; IMPACT_ANALYSIS.md; EXTERNAL_RESEARCH.md; REFERENCES.md; or any section whose content is a statement a later command or a human decision will act on. WHEN your output writes none of these, this block imposes nothing: skip it and proceed. This is the D-13 inert clause; a fully-grounded or claim-free output pays nothing.

2. The unit is the load-bearing claim. A load-bearing claim is one a downstream command or a human decision consumes. A passing aside is not load-bearing; a statement someone will act on is. Apply the rest of this block per load-bearing claim, not per sentence.

3. Ground it or abstain. Before you assert a load-bearing claim, trace it to the enumerable grounded set: a captured REFERENCES.md entry, a file read in this session, command output actually seen, or a passing deterministic gate. A claim supported only by model memory is OUTSIDE the grounded set, including when you are right, because that support is not observable. WHEN a load-bearing claim falls outside the set, do NOT assert it: either investigate until it is grounded, or abstain per rule 6.

4. Status records provenance, never confidence. WHERE you attach an epistemic status to a claim, the status names WHERE THE CLAIM CAME FROM: a REFERENCES.md entry title, a file path plus line, or the gate output it came from. It SHALL NOT express a degree of certainty. Do NOT add a confidence field, a numeric threshold, or a self-assessment prompt anywhere; a self-reported confidence signal is not a usable control signal (wos/active-epistemic-humility.md Part 1.3). A status whose referent slot is empty is read as UNKNOWN, not as a weak yes.

5. Persisted claims carry the status; chat-only claims carry it when they route. Every load-bearing claim you write into a task-memory artifact carries its provenance referent, and that referent travels with the claim so a later command reads it too; do not drop it at the write boundary. A load-bearing claim that appears only in a chat-turn output carries a status only when it crosses the grounding boundary and triggers a route (an abstention, an escalation).

6. Abstain as a routed continuation, never a bare refusal. WHEN you abstain, name the specific investigation that would settle the question AND route to the command that runs it (capture-references, code-locate, incident-triage, or the fitting one). A withholding that stalls the work is invalid output. Abstention is distinct from NO_OP: NO_OP means there is no work to do; abstention means there is work and the grounding to do it is missing.

7. An unfired gate is not evidence. The absence of a fired check does not mean grounding existed. Do not read silence here as a pass.

Standard output layout (required)

Produce the command output using this structure (English only):

Artifact changes

Follow ## Global output contract in WORKFLOW_OPERATING_SYSTEM.md for APPLIED / PROPOSED / SKIP rules.

Command transcript

Brief audit trail (max 4 lines; max 3 in no-op runs with NO_OP_TRACE).

Handoff

Use the adaptive ending format from WORKFLOW_OPERATING_SYSTEM.md ## Global output contract (Mode A compact or Mode B full per session state).

Definition of done (command output)

• All tokens from code AND docs are accounted for in the comparison.
• Each drift finding has: category, token name, code value, doc value, severity, suggested fix.
• If Figma was included: 3-way comparison is complete.
• If everything is in sync, health says so clearly.
• Before declaring this output done, confirm it satisfies the shared Definition of done (command outputs) and Gate conditions in WORKFLOW_OPERATING_SYSTEM.md.

Quality bar: Every finding is grounded in actual code and doc values, not assumptions. If tokens are in sync, say so.