coding-agent-skills 0.2.10 → 0.2.11

package/CHANGELOG.md

@@ -2,6 +2,26 @@
 
 All notable changes follow [Semantic Versioning](docs/versioning/README.md).
 
+## [0.2.11] - 2026-07-03
+
+### Added
+
+- `secret-audit` audit-only skill for redacted static secret exposure detection.
+- `coding-agent-skills secret-audit <project-root>` CLI command.
+- Dependency-free secret audit renderer for high-confidence finding paths, finding types,
+  counts, skipped secret-bearing paths, not-verified credential surfaces, adapter-limited
+  scope, and safety refusals.
+- Synthetic secret-audit fixtures and release tests for generic static scans,
+  adapter-scoped scans, `.env` exclusion, matched-value omission, and repo-map-only adapter
+  skips.
+
+### Changed
+
+- Adapter schemas and validators now recognize `secret-audit` as an audit-only skill while
+  preserving the existing `0.2.3` adapter contract compatibility baseline.
+- Usage, release, safety, architecture, adapter, roadmap, ledger, and run-log docs now
+  describe the new redacted read-only secret-audit command.
+
 ## [0.2.10] - 2026-07-03
 
 ### Added

package/README.md

@@ -8,6 +8,7 @@ The pilot pack contains:
 - `repo-map`: audit-only repository orientation.
 - `route-trace`: audit-only static route surface tracing.
 - `env-audit`: audit-only environment variable name mapping without values.
+- `secret-audit`: audit-only high-confidence secret exposure detection without values.
 - `build-verify`: controlled local validation using existing project commands.
 - `git-preflight`: audit-only Git readiness inspection.
 - `runtime-truth`: audit-only runtime evidence collection.
@@ -42,6 +43,7 @@ Every skill emits the evidence-pack contract. A command being attempted is never
 - From a clone, the same wrapper is available as `bin/coding-agent-skills validate-pack`.
 - Trace static route surfaces with `coding-agent-skills route-trace <project-root>`.
 - Map environment variable names with `coding-agent-skills env-audit <project-root>`.
+- Find redacted secret exposure risks with `coding-agent-skills secret-audit <project-root>`.
 - Validate project adapters against [the formal adapter schema](schemas/project-adapter.schema.json).
 - Review [external adapter discovery](docs/adapters/discovery.md).
 - Run `node scripts/validate-adapters.mjs <adapter-root>` for a disposable external root.
@@ -51,6 +53,8 @@ Every skill emits the evidence-pack contract. A command being attempted is never
   `node scripts/render-adapter-repo-map.mjs <project-root>`.
 - Render a static route-trace report with
   `node scripts/render-route-trace.mjs <project-root>`.
+- Render a redacted secret-audit report with
+  `node scripts/render-secret-audit.mjs <project-root>`.
 - Review [adapter upgrade checks](docs/adapters/upgrades.md).
 - Run `node scripts/check-adapter-upgrade.mjs <before-project-root> <after-project-root>`
   for disposable project revisions.

package/ROADMAP.md

@@ -1,6 +1,6 @@
 # Roadmap
 
-The public package now contains seven approved shared skills. Builder-mode approval is
+The public package now contains eight approved shared skills. Builder-mode approval is
 active for the remaining read-only skill wave in this repository; real-world project
 execution constraints remain unchanged.
 
@@ -32,6 +32,8 @@ execution constraints remain unchanged.
   tracing.
 - `v0.2.10`: audit-only `env-audit` skill and CLI renderer for value-free environment
   variable name mapping.
+- `v0.2.11`: audit-only `secret-audit` skill and CLI renderer for redacted secret
+  exposure detection.
 
 The next milestone is recorded in [work-ledger.md](work-ledger.md). The
 [maintainer loop](RUNBOOK.md) may select and evidence that milestone, but it must stop
@@ -74,18 +76,18 @@ Next safe milestone options:
 |---|---|---|---|
 | `route-trace-skill` | General | Audit-only | Implemented in `v0.2.9` |
 | `env-audit-skill` | General | Audit-only | Implemented in `v0.2.10` |
-| `secret-audit-skill` | General | Audit-only | Builder-mode approved; queued after `env-audit` |
+| `secret-audit-skill` | General | Audit-only | Implemented in `v0.2.11` |
+| `api-contract-audit-skill` | General | Audit-only | Builder-mode approved; next in wave |
+| `migration-review-skill` | General with platform adapters | Audit-only | Builder-mode approved; later in wave |
+| `github-handoff-skill` | General | Audit-only | Builder-mode approved; later in wave |
 | `deployment-preflight-skill` | General | Audit-only | Builder-mode approved; later in wave |
 | `cloudflare-preflight-skill` | Platform-specific | Audit-only | Builder-mode approved; later in wave |
 | `cloudflare-deploy-skill` | Platform-specific | Action-capable | Blocked on approval model |
 | `supabase-rls-audit-skill` | Platform-specific | Audit-only | Builder-mode approved; later in wave |
-| `migration-review-skill` | General with platform adapters | Audit-only | Builder-mode approved; later in wave |
-| `api-contract-audit-skill` | General | Audit-only | Builder-mode approved; later in wave |
 | `repo-knowledge-sync-skill` | General | Action-capable | Blocked on write approval model |
 | `security-hardening-review-skill` | General coordinator | Audit-only | Needs more evidence |
 | `worker-queue-debug-skill` | General core with project adapters | Audit-only first | Needs more evidence |
 | `devvit-ingest-debug-skill` | Project-specific | Audit-only | Needs project evidence |
-| `github-handoff-skill` | General | Audit-only | Builder-mode approved; later in wave |
 | `session-extractor-skill` | General tooling | Action-capable | Blocked on privacy policy and more evidence |
 | `command-redaction-skill` | General tooling | Action-capable | Needs more evidence |
 

package/bin/coding-agent-skills

@@ -35,6 +35,12 @@ const commands = {
     usage: "coding-agent-skills env-audit <project-root>",
     requiredArgs: 1,
   },
+  "secret-audit": {
+    script: "scripts/render-secret-audit.mjs",
+    args: ([projectRoot]) => [projectRoot],
+    usage: "coding-agent-skills secret-audit <project-root>",
+    requiredArgs: 1,
+  },
   "validate-adapters": {
     script: "scripts/validate-adapters.mjs",
     args: ([adapterRoot]) => [adapterRoot],
@@ -53,6 +59,7 @@ function usage(exitCode = 0) {
     "  repo-map <project-root>",
     "  route-trace <project-root>",
     "  env-audit <project-root>",
+    "  secret-audit <project-root>",
     "  validate-adapters <adapter-root>",
     "",
     "local wrapper for the published coding-agent-skills package",

package/docs/adapters/README.md

@@ -70,6 +70,23 @@ secret-bearing files, and reports variable names, classifications, sample files
 skipped items, and not-verified runtime or credential stores. It never prints values or
 validates credentials.
 
+## Adapter-Aware Secret Audit Consumption
+
+The shared pack can consume a validated project-owned adapter as bounded context for
+`secret-audit`:
+
+```bash
+node scripts/render-secret-audit.mjs <project-root>
+```
+
+The renderer validates the project declaration when present. If an adapter is present but
+does not enable `secret-audit`, it reports an adapter-limited skip instead of broadening
+scope. When enabled, it reads only adapter-declared safe paths, excludes `.env`,
+secret-bearing files, generated output, dependency paths, and oversized files, then
+reports finding paths, types, and counts. It never prints matched values, validates
+credentials, rotates secrets, contacts APIs, deploys, migrates, builds, tests, or mutates
+project files.
+
 ## What Adapters May Do
 
 - Add bounded relative read paths and ignored paths.
@@ -77,6 +94,8 @@ validates credentials.
 - Add documentation precedence and package-manager hints.
 - Add route-trace safe read paths for static route files and route config.
 - Add env-audit safe read paths for static source, docs, sample, and config files.
+- Add secret-audit safe read paths for static source, docs, sample, and config files
+  while relying on the shared scanner to exclude secret-bearing paths.
 - Add command aliases that already satisfy the shared command policy.
 - Add status-only runtime commands and manager hints.
 - Require additional evidence or named approval for exceptional reads.

package/docs/adapters/project-installation.md

@@ -133,6 +133,18 @@ present but does not enable `env-audit`, it reports an adapter-limited skip. Whe
 it reads only adapter-declared safe paths, refuses `.env` and secret-bearing files, and
 reports environment variable names without values.
 
+A project-owned adapter can also enable read-only `secret-audit` context:
+
+```bash
+node scripts/render-secret-audit.mjs <project-root>
+```
+
+The secret-audit renderer validates the project declaration when present. If the adapter
+is present but does not enable `secret-audit`, it reports an adapter-limited skip. When
+enabled, it reads only adapter-declared safe paths, refuses `.env` and secret-bearing
+files, and reports high-confidence finding paths, types, and counts without matched
+values or credential validation.
+
 ## Safety Boundary
 
 Project adapters are extension-only. They cannot remove denied operations, change an

package/docs/adapters/real-project-adoption.md

@@ -21,7 +21,7 @@ project repository is touched:
 - The project can declare exactly one installation file: `.coding-agent/skills.json` or
   `coding-agent.skills.json`.
 - The adapter need is bounded to existing pilot skills: `repo-map`, `route-trace`,
-  `env-audit`, `build-verify`, `git-preflight`, `runtime-truth`, or
+  `env-audit`, `secret-audit`, `build-verify`, `git-preflight`, `runtime-truth`, or
   `llm-drift-control`.
 - The adapter can narrow context with relative paths, documentation precedence, safe
   aliases, status-only hints, or extra evidence requirements.

package/docs/architecture/README.md

@@ -14,6 +14,7 @@ Audit-only:
 - `repo-map`
 - `route-trace`
 - `env-audit`
+- `secret-audit`
 - `git-preflight`
 - `runtime-truth`
 - `llm-drift-control`
@@ -22,6 +23,6 @@ Controlled local validation:
 
 - `build-verify`
 
-The evidence pack is a shared output contract, not an executable skill. Environment and
-secret audits, deployment preflight, GitHub handoff, provider operations, and additional
-project adapters remain separate future work.
+The evidence pack is a shared output contract, not an executable skill. Deployment
+preflight, GitHub handoff, provider operations, and additional project adapters remain
+separate future work.

package/docs/release/README.md

@@ -19,8 +19,9 @@
 13. Inspect tarball contents for local-only files, credentials, `.env` files, dependency
     folders, generated output, and unrelated repositories.
 14. Install the tarball into a temporary npm prefix and smoke-test the installed CLI.
-15. Smoke-test any new CLI command such as `coding-agent-skills route-trace` or
-    `coding-agent-skills env-audit` against synthetic fixtures only unless a real project
+15. Smoke-test any new CLI command such as `coding-agent-skills route-trace`,
+    `coding-agent-skills env-audit`, or `coding-agent-skills secret-audit` against
+    synthetic fixtures only unless a real project
     read-only smoke is explicitly approved.
 16. Review changelog, ledger, run evidence, and versioning impact.
 17. Commit with approved identity.

package/docs/release/npm-package.md

@@ -7,7 +7,7 @@ safety model.
 ## Current Package Shape
 
 - Package name: `coding-agent-skills`.
-- Package version: `0.2.10`.
+- Package version: `0.2.11`.
 - CLI bin: `coding-agent-skills` mapped to `bin/coding-agent-skills`.
 - Module type: `module`.
 - Dependencies: none.
@@ -29,6 +29,7 @@ coding-agent-skills validate-project /path/to/project
 coding-agent-skills repo-map /path/to/project
 coding-agent-skills route-trace /path/to/project
 coding-agent-skills env-audit /path/to/project
+coding-agent-skills secret-audit /path/to/project
 coding-agent-skills validate-adapters /path/to/adapter-root
 ```
 
@@ -43,6 +44,9 @@ project-adapter validators. `route-trace` is static and audit-only; it reports r
 files and route declarations without executing the target project. `env-audit` is static
 and audit-only; it reports environment variable names without reading `.env` files or
 printing values.
+`secret-audit` is static and audit-only; it reports high-confidence secret-like finding
+paths, types, and counts without printing matched values, reading `.env` files, or
+validating credentials.
 
 `coding-agent-skills validate-pack` is package-aware. In a source checkout, it keeps
 source-only checks such as `.gitignore` validation. In an installed package tree, where
@@ -77,7 +81,7 @@ included.
 
 The public CLI remains read-only for target projects unless a specific underlying skill
 already permits a bounded local validation action. The installed `repo-map`,
-`route-trace`, and adapter flows do not:
+`route-trace`, `env-audit`, `secret-audit`, and adapter flows do not:
 
 - deploy
 - run migrations

package/docs/safety/README.md

@@ -2,7 +2,7 @@
 
 ## Audit-Only Rule
 
-`repo-map`, `route-trace`, `env-audit`, `git-preflight`, `runtime-truth`, and `llm-drift-control` must not alter project files, Git state, dependencies, processes, services, databases, remote systems, or deployment state.
+`repo-map`, `route-trace`, `env-audit`, `secret-audit`, `git-preflight`, `runtime-truth`, and `llm-drift-control` must not alter project files, Git state, dependencies, processes, services, databases, remote systems, or deployment state.
 
 `route-trace` is static only. It may read bounded non-secret route files and route
 configuration, but it must not execute app code, run servers, hit URLs, claim runtime
@@ -12,6 +12,11 @@ truth, or broaden adapter scope when a project adapter is present.
 files, including `.env.example`, but must not read `.env`, print values, validate
 credentials, contact APIs, or inspect secret stores.
 
+`secret-audit` is redacted static inspection only. It may read bounded non-secret static
+files and report high-confidence secret-like finding paths, types, and counts, but it must
+not print matched values, read `.env` or secret-bearing files, inspect credential stores,
+validate or rotate credentials, contact APIs, or broaden adapter scope.
+
 `build-verify` may run existing project-native validation commands. Build or test tools may create their normal local artifacts, but the skill must declare observed changes and must reject installation, fix modes, snapshot updates, deployment, migration, or unknown scripts.
 
 ## Restricted Categories

package/docs/testing/README.md

@@ -44,6 +44,14 @@ Synthetic env-audit projects cover value-free variable-name detection, `.env` ex
 behavior. Env-audit tests must never print values, validate credentials, contact APIs,
 run target projects, build, test, deploy, migrate, or read `.env` files.
 
+## Secret Audit
+
+Synthetic secret-audit projects cover high-confidence finding detection, `.env` exclusion,
+matched-value omission, adapter-declared scope, and adapter-present-but-not-enabled
+behavior. Secret-audit tests construct synthetic secret-like values only in temporary
+directories and assert that rendered reports include paths, types, and counts without
+printing matched values.
+
 ## Privacy And Redaction
 
 Sensitive shapes are stored as ordered synthetic parts and reconstructed only in memory. Tests verify type detection, redaction, and absence from reusable skill content without printing fixture values.

package/docs/usage/README.md

@@ -7,6 +7,7 @@ Select the least-privileged skill that matches the request:
 | Understand repository identity and structure | `repo-map` |
 | Trace statically visible route surfaces | `route-trace` |
 | Map environment variable names without values | `env-audit` |
+| Find high-confidence secret exposure risks without values | `secret-audit` |
 | Run existing local validation checks | `build-verify` |
 | Assess Git handoff readiness | `git-preflight` |
 | Determine what is actually running | `runtime-truth` |
@@ -18,11 +19,13 @@ Select the least-privileged skill that matches the request:
 2. Use `route-trace` when route files or declarations must be mapped from static files.
 3. Use `env-audit` when environment variable names or sample config references must be
    mapped without reading values.
-4. Perform implementation outside this pilot pack.
-5. Use `build-verify` for approved project-native checks.
-6. Use `git-preflight` before handoff or publication.
-7. Use `runtime-truth` only when live local state matters.
-8. Use `llm-drift-control` when claims and evidence may disagree.
+4. Use `secret-audit` when high-confidence tracked secret exposure risk must be reported
+   by path, type, and count without printing matched values.
+5. Perform implementation outside this pilot pack.
+6. Use `build-verify` for approved project-native checks.
+7. Use `git-preflight` before handoff or publication.
+8. Use `runtime-truth` only when live local state matters.
+9. Use `llm-drift-control` when claims and evidence may disagree.
 
 Every skill emits an evidence pack. Read `status`, skipped checks, failures, confidence, and changed state before relying on a completion claim.
 
@@ -55,6 +58,7 @@ coding-agent-skills validate-project /path/to/project
 coding-agent-skills repo-map /path/to/project
 coding-agent-skills route-trace /path/to/project
 coding-agent-skills env-audit /path/to/project
+coding-agent-skills secret-audit /path/to/project
 coding-agent-skills validate-adapters /path/to/adapter-root
 ```
 
@@ -74,6 +78,9 @@ skipped items, and not-verified runtime-dependent route classes.
 when enabled, and statically reports environment variable names, classifications, sample
 files inspected, skipped secret-bearing paths, and not-verified runtime or credential
 stores without printing values.
+`secret-audit` validates a project adapter when present, uses adapter-declared safe paths
+when enabled, and statically reports high-confidence secret-like finding paths, types, and
+counts without printing matched values or validating credentials.
 
 The installed CLI does not run target project builds or tests, perform runtime checks,
 deploy, migrate, mutate services or processes, or read `.env` files. Project adapters
@@ -89,6 +96,7 @@ bin/coding-agent-skills validate-project /path/to/project
 bin/coding-agent-skills repo-map /path/to/project
 bin/coding-agent-skills route-trace /path/to/project
 bin/coding-agent-skills env-audit /path/to/project
+bin/coding-agent-skills secret-audit /path/to/project
 bin/coding-agent-skills validate-adapters /path/to/adapter-root
 ```
 
@@ -101,6 +109,7 @@ coding-agent-skills validate-project /path/to/project
 coding-agent-skills repo-map /path/to/project
 coding-agent-skills route-trace /path/to/project
 coding-agent-skills env-audit /path/to/project
+coding-agent-skills secret-audit /path/to/project
 coding-agent-skills validate-adapters /path/to/adapter-root
 ```
 

package/examples/command-policies/secret-audit.json

@@ -0,0 +1,71 @@
+{
+  "version": "0.2.3",
+  "mode": "audit-only",
+  "parserPolicy": {
+    "inspectEverySegment": true,
+    "inspectScriptBodies": true,
+    "rejectUnknownExecutables": true,
+    "rejectShellWrappers": true,
+    "rejectHeredocs": true,
+    "rejectRedirection": true,
+    "providerSpecificNpx": true,
+    "authenticatedCurlRequiresApproval": true,
+    "boundedReadsRequired": true,
+    "allowedComposition": "read-only"
+  },
+  "allowedFamilies": [
+    {
+      "name": "bounded-secret-pattern-inspection",
+      "executables": ["pwd", "ls", "rg", "find", "sed", "head"],
+      "argumentPolicy": {
+        "strategy": "pattern",
+        "allowedPatterns": ["bounded repository-local path/count secret-pattern inspection"],
+        "deniedPatterns": ["secret files, matched values, credential stores, API calls, and unbounded traversal"]
+      },
+      "constraints": [
+        "Remain inside the declared project scope.",
+        "Bound traversal depth and output.",
+        "Exclude .env, secret-bearing, generated, dependency, build, and runtime-output paths.",
+        "Report file paths, finding types, and counts only."
+      ]
+    },
+    {
+      "name": "git-identity-inspection",
+      "executables": ["git"],
+      "argumentPolicy": {
+        "strategy": "exact",
+        "allowedPatterns": ["rev-parse and status --short --branch"],
+        "deniedPatterns": ["all Git mutation and publication subcommands"]
+      },
+      "constraints": ["Allow only read-only repository identity and branch-state inspection."]
+    },
+    {
+      "name": "secret-audit-renderer",
+      "executables": ["node", "coding-agent-skills"],
+      "argumentPolicy": {
+        "strategy": "exact",
+        "allowedPatterns": ["node scripts/render-secret-audit.mjs <project-root>; coding-agent-skills secret-audit <project-root>"],
+        "deniedPatterns": [".env reads, matched values, credential validation, rotation, API calls, builds, tests, deployment, migration, and package installation"]
+      },
+      "constraints": [
+        "The renderer must remain static and read-only.",
+        "Do not print matched values or treat findings as credential validity evidence."
+      ]
+    }
+  ],
+  "restrictedCategories": [
+    "file-write",
+    "package-install",
+    "deployment",
+    "git-mutation",
+    "unrestricted-scan",
+    "secret-read",
+    "process-mutation",
+    "service-mutation",
+    "migration-apply",
+    "privileged-api"
+  ],
+  "approvalExceptions": [
+    "A named-file approval may permit one otherwise excluded non-mutating static read when the file is not secret-bearing."
+  ]
+}

package/examples/evidence-packs/secret-audit.json

@@ -0,0 +1,55 @@
+{
+  "contractVersion": "1.0.0",
+  "skill": {"name": "secret-audit", "version": "0.2.3"},
+  "invocation": {
+    "id": "example-secret-audit",
+    "startedAt": "2026-07-03T11:00:00Z",
+    "endedAt": "2026-07-03T11:01:00Z"
+  },
+  "repository": {
+    "root": "/workspace/example-project",
+    "branch": "main",
+    "head": "0123456789abcdef",
+    "workingTreeState": "clean"
+  },
+  "userIntent": "Find possible tracked secret exposure before handoff.",
+  "declaredScope": ["/workspace/example-project"],
+  "projectAdapter": "example-secret-adapter",
+  "environmentSummary": {"platform": "linux", "shell": "bash"},
+  "status": "complete",
+  "confidence": {
+    "level": "high",
+    "reason": "Static files were scanned for high-confidence secret-like patterns with matched values omitted."
+  },
+  "commands": [
+    {
+      "command": "coding-agent-skills secret-audit /workspace/example-project",
+      "family": "secret-audit-renderer",
+      "workingDirectory": "/workspace/example-project",
+      "startedAt": "2026-07-03T11:00:20Z",
+      "endedAt": "2026-07-03T11:00:21Z",
+      "exitStatus": 0,
+      "resultStatus": "success",
+      "safetyClass": "allowed",
+      "approvalReference": null,
+      "purpose": "Render a redacted static secret-audit report.",
+      "outputSummary": "Reported finding paths, types, and counts without matched values."
+    }
+  ],
+  "skippedChecks": [],
+  "findings": [
+    {
+      "summary": "Potential secret exposure was reported by file path, type, and count only.",
+      "evidence": ["src/example.ts"]
+    }
+  ],
+  "risks": [],
+  "failures": [],
+  "unresolvedQuestions": [],
+  "changedState": {
+    "changed": false,
+    "summary": "No project, Git, dependency, runtime, service, or remote state changed."
+  },
+  "handoffSummary": "Secret-like findings require human review; matched values were omitted.",
+  "recommendedNextAction": "Review flagged files locally and rotate credentials only through approved project procedures."
+}

package/examples/manifests/secret-audit.json

@@ -0,0 +1,14 @@
+{
+  "name": "secret-audit",
+  "version": "0.2.3",
+  "mode": "audit-only",
+  "evidenceContract": "../../contracts/evidence-pack/evidence-pack.schema.json",
+  "commandPolicy": "../command-policies/secret-audit.json",
+  "adapterSchema": "../../schemas/project-adapter.schema.json",
+  "adapterCompatibility": {
+    "contractVersion": "1.0.0",
+    "compatibleAdapterVersions": ["1.0.0"]
+  },
+  "adapterInterface": "../../skills/secret-audit/adapter-interface.md",
+  "description": "Find high-confidence secret exposure risks without printing values."
+}

package/examples/workflows/secret-audit.md

@@ -0,0 +1,10 @@
+# Secret Audit Workflow
+
+Use `secret-audit` before handoff or publication:
+
+```bash
+coding-agent-skills secret-audit /workspace/project
+```
+
+Review file paths, types, counts, skipped secret-bearing paths, and not-verified stores.
+Do not ask the tool to print matched values or rotate credentials.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "coding-agent-skills",
-  "version": "0.2.10",
+  "version": "0.2.11",
   "description": "Evidence-first, read-only coding-agent skills and project adapter tooling.",
   "type": "module",
   "private": false,
@@ -11,6 +11,7 @@
     "repo-map",
     "route-trace",
     "env-audit",
+    "secret-audit",
     "project-adapters",
     "code-validation",
     "cli"

package/runs/skill-runs.md

@@ -197,3 +197,19 @@ This file records bounded maintainer-loop runs. Entries must not contain secrets
 - Validation commands: pending final release validation matrix.
 - Result: pass pending final publication evidence.
 - Commit/tag/push status: pending approved release workflow.
+
+## implementation-v0.2.11-secret-audit
+
+- Run ID: `implementation-v0.2.11-secret-audit`
+- Repository: `/home/oneclickwebsitedesignfactory/coding-agent-skills`
+- Command used: `builder-mode approval for secret-audit-skill implementation and release`
+- Files changed: `secret-audit` skill, secret-audit renderer and library, CLI wrapper,
+  adapter schemas, pack rules, release tests, synthetic secret fixtures, usage/release/
+  safety/adapter docs, changelog, roadmap, work ledger, run log, and package metadata.
+- Safety boundary: read-only, static-analysis only, no `.env` reads, no secret-file
+  reads, no matched value printing, no credential validation or rotation, no API calls,
+  no builds, no tests in target projects, no deploys, no migrations, and no
+  target-project mutation.
+- Validation commands: pending final release validation matrix.
+- Result: pass pending final publication evidence.
+- Commit/tag/push status: pending approved release workflow.

package/schemas/project-adapter-installation.schema.json

@@ -67,6 +67,7 @@
           "repo-map",
           "route-trace",
           "env-audit",
+          "secret-audit",
           "build-verify",
           "git-preflight",
           "runtime-truth",
@@ -101,6 +102,7 @@
               "repo-map",
               "route-trace",
               "env-audit",
+              "secret-audit",
               "build-verify",
               "git-preflight",
                 "runtime-truth",

package/schemas/project-adapter.schema.json

@@ -91,6 +91,7 @@
               "repo-map",
               "route-trace",
               "env-audit",
+              "secret-audit",
               "build-verify",
               "git-preflight",
               "runtime-truth",
@@ -169,6 +170,7 @@
                   "repo-map",
                   "route-trace",
                   "env-audit",
+                  "secret-audit",
                   "build-verify",
                   "git-preflight",
                   "runtime-truth",

package/scripts/lib/pack-rules.mjs

@@ -2,6 +2,7 @@ export const PILOT_SKILLS = [
   "repo-map",
   "route-trace",
   "env-audit",
+  "secret-audit",
   "build-verify",
   "git-preflight",
   "runtime-truth",
@@ -15,6 +16,7 @@ export const AUDIT_ONLY_SKILLS = [
   "repo-map",
   "route-trace",
   "env-audit",
+  "secret-audit",
   "git-preflight",
   "runtime-truth",
   "llm-drift-control",
@@ -380,6 +382,13 @@ export function classifyTrigger(prompt) {
   ) {
     return "env-audit";
   }
+  if (
+    /\b(?:secret audit|secrets? scan|secret exposure|credential exposure|tracked secrets?|hardcoded secrets?|private keys?|api keys?|tokens? in source)\b/.test(
+      text,
+    )
+  ) {
+    return "secret-audit";
+  }
   if (
     /\b(?:unfamiliar repository|canonical repository root|canonical repo|map the current packages|map this repository|identify its entry points|nested directory)\b/.test(
       text,
@@ -521,7 +530,7 @@ function classifySegment(segment, options = {}) {
   }
   if (
     executable === "node" &&
-    !/^node\s+(?:--check\b|--test\b|scripts\/(?:validate-pack|validate-maintainer-loop|validate-adapters|validate-project-adapters|check-adapter-upgrade|check-adapter-upgrade-chain|verify-evidence-bundle|render-evidence-archive-report|render-adapter-repo-map|render-route-trace|render-env-audit|test-pack)\.mjs\b)/.test(
+    !/^node\s+(?:--check\b|--test\b|scripts\/(?:validate-pack|validate-maintainer-loop|validate-adapters|validate-project-adapters|check-adapter-upgrade|check-adapter-upgrade-chain|verify-evidence-bundle|render-evidence-archive-report|render-adapter-repo-map|render-route-trace|render-env-audit|render-secret-audit|test-pack)\.mjs\b)/.test(
       segment,
     )
   ) {
@@ -531,7 +540,7 @@ function classifySegment(segment, options = {}) {
     ["coding-agent-skills", "bin/coding-agent-skills", "./bin/coding-agent-skills"].includes(
       executable,
     ) &&
-    !/^(?:\.\/)?(?:bin\/)?coding-agent-skills\s+(?:validate-pack|validate-project\s+\S+|repo-map\s+\S+|route-trace\s+\S+|env-audit\s+\S+|validate-adapters\s+\S+|help|--help|-h)\s*$/.test(
+    !/^(?:\.\/)?(?:bin\/)?coding-agent-skills\s+(?:validate-pack|validate-project\s+\S+|repo-map\s+\S+|route-trace\s+\S+|env-audit\s+\S+|secret-audit\s+\S+|validate-adapters\s+\S+|help|--help|-h)\s*$/.test(
       segment,
     )
   ) {