@plainconceptsplatform/agent-harness 3.5.0 → 3.7.0

package/skills/pc-make-guardrails/category-reference.md

@@ -1,112 +1,112 @@
-# Guardrails category reference
-
-From the documents and code graph analysis, extract the rules an agent could break without noticing. Only include a category if you found real evidence for it.
-
-- Architecture constraints: layer boundaries, module dependencies, forbidden imports, directory ownership rules (e.g. "src/api/ must not import from src/ui/"). Verify actual import boundaries with the project-selected analysis tools.
-- File organization: the god-files and dumping-ground constants this project has already accumulated, named. The general principle is in `pc-guardrails-generic`; what belongs here is where this codebase keeps breaking it.
-- Naming conventions: file naming, component naming, API route conventions, branch naming
-- Code style: formatter config, lint rules, import ordering, max line length. Derive from actual config files.
-- Testing rules: test file locations, naming, coverage gates, what must be tested before merge
-- Build & deployment: build commands, env requirements, deployment targets, CI gates
-- Data & state: migration rules, schema change process, state management patterns
-- Security: auth boundaries, input validation requirements, secrets handling
-- Dependencies: package manager, lockfile rules, upgrade policy, forbidden packages
-- Git workflow: branch naming, commit message format, PR process (platform-specific from `harness.json`)
-- Domain-specific rules: anything in `openspec/config.yaml` context or `ARCHITECTURE.md` constraints/risks sections
-
-Each rule must be:
-
-- **Negative.** State the boundary and what breaks when it is crossed, not the behaviour you want: `Never import Microsoft.EntityFrameworkCore.* in Application; it is a layer violation and the build does not catch it`, not `Keep Application framework-free`. A prohibition removes an option; a preference competes with everything else the model knows about writing code, and loses.
-- **Concrete**: "Use `pnpm` not `npm`" not "Use the right package manager".
-- **Evidence-based**: derived from the files and code graph you analyzed. Never invent a rule the project does not state or demonstrate somewhere.
-- **Not enforced elsewhere.** Skip anything the formatter, linter, type checker, test suite, CI gate or a harness plugin already fails the build on. A rule restating `biome.json` is read on every load and changes nothing: the build was going to catch it. Write the rules that nothing but a careful reader would catch.
-- **Not already in `pc-guardrails-generic`.** That skill loads alongside this one, every request. Secrets, zero-comment default, scratch-file location, one-responsibility-per-file, minimal-test discipline, and the engineer workflow are its rules, not this file's.
-
-**At most 40 rules, across all categories.** Rank by what a violation costs and cut from the bottom; a category with nothing consequential in it gets no rules at all. This cap is the point of the exercise, not tidiness: compliance falls away as a rule file grows, so the 41st rule does not just cost its own tokens, it dilutes the 40 that matter. If more than 40 survive every bar above, the excess is a sign the project's constraints belong in a linter rule or a CI check instead.
-
-## Contrastive example
-
-**Bad** (reference fact — cut):
-> - The SQL Server database name is `myapp`, lowercase.
-
-The agent reads the connection string in config. It costs tokens on every load and the agent cannot "break" it.
-
-**Good** (negative constraint with consequence — keep):
-> - Never add a cached column for a value that is derived from another entity; a later edit to the source leaves the cache stale, and nothing in the build catches it.
-
-The agent could break this without noticing, nothing mechanically enforces it, and the consequence is stated.
-
-## Skill template
-
-Each section holds constraints an agent could break without noticing, not reference facts. "Naming Conventions" does not mean "list how files are named" — it means "name the conventions whose violation is silent and costly." "Build & Deployment" does not mean "list the build commands" — it means "name the build rules a developer could violate without CI catching it." If a section has only reference facts, omit it entirely.
-
-Write (or update) `.agents/skills/pc-guardrails-project/SKILL.md`:
-
-```markdown
----
-name: pc-guardrails-project
-description: Project-specific rules and constraints extracted from ARCHITECTURE.md. Load this skill before implementing any change to understand boundaries, conventions, and constraints for this codebase.
-license: MIT
----
-
-# Project Guardrails
-
-> Auto-generated by `/make-guardrails`. Regenerate with the same command when architecture or conventions change.
-
-## Architecture Constraints
-- <rule>
-- <rule>
-
-## Naming Conventions
-- <rule>
-
-## Code Style
-- <rule>
-
-## Testing
-- <rule>
-
-## Build & Deployment
-- <rule>
-
-## Data & State
-- <rule>
-
-## Security
-- <rule>
-
-## Dependencies
-- <rule>
-
-## Git Workflow
-- <rule>
-
-<!-- Last updated: <current ISO timestamp> -->
-```
-
-Only include sections that have real rules. Omit empty sections.
-
-## Self-check (before writing the file)
-
-Re-read the output you are about to write. Then:
-
-1. **Count the rules** (every bullet under every section). If there are more than 40, cut from the bottom — rank by what a violation costs and remove the cheapest until you are at or under 40. A rule file past 40 dilutes the ones that matter.
-
-2. **Scan for positive phrasing and reference facts.** Cut or rewrite any rule that:
-   - States what something is named, rather than what must not be named that way and why.
-   - Lists a port number, a database name, a package version, a SDK version, or a connection string. The agent discovers these by reading config.
-   - Describes how something works (e.g. "auth uses a smart scheme that forwards to JWT or Cookies"), rather than what must not be done with it.
-   - Restates a project's tech stack as a list ("Frontend: React 19, Next.js 15, TypeScript…"). That is reference material, not a constraint.
-
-3. **Strip anything already enforced by tooling.** Remove a rule if any of these already fails the build on its violation:
-   - Biome / ESLint / Prettier / Steiger / lint:fsd
-   - NetArchTest / architecture test projects
-   - Semgrep / Trivy / TruffleHog / SBOM checks
-   - Coverage gates (`scripts/check-coverage.mjs`)
-   - `.editorconfig`, `Directory.Build.props`, NuGet audit gates
-   - CI workflow steps (`app-ci.yml`, `ci.yml`)
-   - GitHub branch protection / required checks. If the build catches it, the rule costs tokens and adds nothing. The only exception is a rule whose enforcement is partial or non-obvious (e.g. architecture tests enforce layering but a developer could still import a namespace through reflection or a transitive dependency — that nuance is worth a rule).
-
-4. **Strip anything already in `pc-guardrails-generic`.** That skill loads on every request alongside this one. Its rules are: secrets discipline, zero-comment default (WHY not WHAT, 10% ceiling, no auto-generated docstrings), scratch-file location, one-responsibility-per-file, minimal-test discipline (one regression test per bug, no framework/library tests, no integration/e2e/snapshot unless asked, no mock-assertion of third-party calls), and the engineer workflow. Do not restate any of them here.
-
-5. **Re-count after cutting.** If you are still over 40, you are writing reference material, not constraints. Cut harder.
+# Guardrails category reference
+
+From the documents and code graph analysis, extract the rules an agent could break without noticing. Only include a category if you found real evidence for it.
+
+- Architecture constraints: layer boundaries, module dependencies, forbidden imports, directory ownership rules (e.g. "src/api/ must not import from src/ui/"). Verify actual import boundaries with the project-selected analysis tools.
+- File organization: the god-files and dumping-ground constants this project has already accumulated, named. The general principle is in `pc-guardrails-generic`; what belongs here is where this codebase keeps breaking it.
+- Naming conventions: file naming, component naming, API route conventions, branch naming
+- Code style: formatter config, lint rules, import ordering, max line length. Derive from actual config files.
+- Testing rules: test file locations, naming, coverage gates, what must be tested before merge
+- Build & deployment: build commands, env requirements, deployment targets, CI gates
+- Data & state: migration rules, schema change process, state management patterns
+- Security: auth boundaries, input validation requirements, secrets handling
+- Dependencies: package manager, lockfile rules, upgrade policy, forbidden packages
+- Git workflow: branch naming, commit message format, PR process (platform-specific from `harness.json`)
+- Domain-specific rules: anything in `openspec/config.yaml` context or `ARCHITECTURE.md` constraints/risks sections
+
+Each rule must be:
+
+- **Negative.** State the boundary and what breaks when it is crossed, not the behaviour you want: `Never import Microsoft.EntityFrameworkCore.* in Application; it is a layer violation and the build does not catch it`, not `Keep Application framework-free`. A prohibition removes an option; a preference competes with everything else the model knows about writing code, and loses.
+- **Concrete**: "Use `pnpm` not `npm`" not "Use the right package manager".
+- **Evidence-based**: derived from the files and code graph you analyzed. Never invent a rule the project does not state or demonstrate somewhere.
+- **Not enforced elsewhere.** Skip anything the formatter, linter, type checker, test suite, CI gate or a harness plugin already fails the build on. A rule restating `biome.json` is read on every load and changes nothing: the build was going to catch it. Write the rules that nothing but a careful reader would catch.
+- **Not already in `pc-guardrails-generic`.** That skill loads alongside this one, every request. Secrets, zero-comment default, scratch-file location, one-responsibility-per-file, minimal-test discipline, and the engineer workflow are its rules, not this file's.
+
+**At most 40 rules, across all categories.** Rank by what a violation costs and cut from the bottom; a category with nothing consequential in it gets no rules at all. This cap is the point of the exercise, not tidiness: compliance falls away as a rule file grows, so the 41st rule does not just cost its own tokens, it dilutes the 40 that matter. If more than 40 survive every bar above, the excess is a sign the project's constraints belong in a linter rule or a CI check instead.
+
+## Contrastive example
+
+**Bad** (reference fact — cut):
+> - The SQL Server database name is `myapp`, lowercase.
+
+The agent reads the connection string in config. It costs tokens on every load and the agent cannot "break" it.
+
+**Good** (negative constraint with consequence — keep):
+> - Never add a cached column for a value that is derived from another entity; a later edit to the source leaves the cache stale, and nothing in the build catches it.
+
+The agent could break this without noticing, nothing mechanically enforces it, and the consequence is stated.
+
+## Skill template
+
+Each section holds constraints an agent could break without noticing, not reference facts. "Naming Conventions" does not mean "list how files are named" — it means "name the conventions whose violation is silent and costly." "Build & Deployment" does not mean "list the build commands" — it means "name the build rules a developer could violate without CI catching it." If a section has only reference facts, omit it entirely.
+
+Write (or update) `.agents/skills/pc-guardrails-project/SKILL.md`:
+
+```markdown
+---
+name: pc-guardrails-project
+description: Project-specific rules and constraints extracted from ARCHITECTURE.md. Load this skill before implementing any change to understand boundaries, conventions, and constraints for this codebase.
+license: MIT
+---
+
+# Project Guardrails
+
+> Auto-generated by `/make-guardrails`. Regenerate with the same command when architecture or conventions change.
+
+## Architecture Constraints
+- <rule>
+- <rule>
+
+## Naming Conventions
+- <rule>
+
+## Code Style
+- <rule>
+
+## Testing
+- <rule>
+
+## Build & Deployment
+- <rule>
+
+## Data & State
+- <rule>
+
+## Security
+- <rule>
+
+## Dependencies
+- <rule>
+
+## Git Workflow
+- <rule>
+
+<!-- Last updated: <current ISO timestamp> -->
+```
+
+Only include sections that have real rules. Omit empty sections.
+
+## Self-check (before writing the file)
+
+Re-read the output you are about to write. Then:
+
+1. **Count the rules** (every bullet under every section). If there are more than 40, cut from the bottom — rank by what a violation costs and remove the cheapest until you are at or under 40. A rule file past 40 dilutes the ones that matter.
+
+2. **Scan for positive phrasing and reference facts.** Cut or rewrite any rule that:
+   - States what something is named, rather than what must not be named that way and why.
+   - Lists a port number, a database name, a package version, a SDK version, or a connection string. The agent discovers these by reading config.
+   - Describes how something works (e.g. "auth uses a smart scheme that forwards to JWT or Cookies"), rather than what must not be done with it.
+   - Restates a project's tech stack as a list ("Frontend: React 19, Next.js 15, TypeScript…"). That is reference material, not a constraint.
+
+3. **Strip anything already enforced by tooling.** Remove a rule if any of these already fails the build on its violation:
+   - Biome / ESLint / Prettier / Steiger / lint:fsd
+   - NetArchTest / architecture test projects
+   - Semgrep / Trivy / TruffleHog / SBOM checks
+   - Coverage gates (`scripts/check-coverage.mjs`)
+   - `.editorconfig`, `Directory.Build.props`, NuGet audit gates
+   - CI workflow steps (`app-ci.yml`, `ci.yml`)
+   - GitHub branch protection / required checks. If the build catches it, the rule costs tokens and adds nothing. The only exception is a rule whose enforcement is partial or non-obvious (e.g. architecture tests enforce layering but a developer could still import a namespace through reflection or a transitive dependency — that nuance is worth a rule).
+
+4. **Strip anything already in `pc-guardrails-generic`.** That skill loads on every request alongside this one. Its rules are: secrets discipline, zero-comment default (WHY not WHAT, 10% ceiling, no auto-generated docstrings), scratch-file location, one-responsibility-per-file, minimal-test discipline (one regression test per bug, no framework/library tests, no integration/e2e/snapshot unless asked, no mock-assertion of third-party calls), and the engineer workflow. Do not restate any of them here.
+
+5. **Re-count after cutting.** If you are still over 40, you are writing reference material, not constraints. Cut harder.

package/skills/pc-make-merge-risk-assess/SKILL.md

@@ -1,70 +1,70 @@
----
-name: pc-make-merge-risk-assess
-description: Generate or update the pc-merge-risk-assess skill from project guardrails and architecture. Produces a PR-level risk assessment that loop recipes can gate automerge on. Invoked by the /make-merge-risk-assess command and the repo-initialize flow.
-license: MIT
----
-
-# Make Merge Risk Assess
-
-Analyze `ARCHITECTURE.md`, the project guardrails skill, and other project files to generate or update an `pc-merge-risk-assess` skill: a checklist of risk indicators that an AI agent evaluates before auto-merging a pull request. When any indicator matches, the agent blocks automerge and leaves the PR for human review with an explanation.
-
-## Steps
-
-1. **Check current state**
-
-   Read `.agents/skills/pc-merge-risk-assess/SKILL.md`. Determine which mode to use:
-   - Does not exist: Generate mode. Create from scratch.
-   - Exists and has a `<!-- Last updated:` footer: Update mode. Incrementally update.
-   - Exists but no timestamp: proceed in Generate mode (full regeneration).
-
-2a. **Generate mode: read source documents**
-
-   Read ALL of the following that exist:
-   - `.agents/skills/pc-guardrails-project/SKILL.md` (primary source — project-specific constraints)
-   - `.agents/skills/pc-guardrails-generic/SKILL.md` (generic safety rules)
-   - `ARCHITECTURE.md` (architecture boundaries, critical paths)
-   - `AGENTS.md` (non-negotiable constraints, verification rules)
-   - `.opencode/harness.json` (platform, concurrency)
-   - CI/CD workflows: `.github/workflows/*`, `azure-pipelines.yml`: whatever exists
-   - Loop recipes: `.loops/recipes/*-loop.yaml` (understand the automerge flow)
-
-   Use file tools to discover risk-critical code paths: `grep` for calculation engines, audit appenders, auth middleware, schema migrations, permission checks, and other sensitive areas.
-
-2b. **Update mode: incremental analysis**
-
-   Extract the `<!-- Last updated: <ISO date> -->` timestamp from the existing skill file. Then:
-   - Read `.agents/skills/pc-guardrails-project/SKILL.md` and check its `<!-- Last updated:` timestamp. If the guardrails haven't changed and ARCHITECTURE.md hasn't changed since the risk skill was last generated, report "Merge risk assessment up to date" and stop.
-   - Run `git log --oneline --since="<date>" -- <relevant config and architecture files>` to find what changed.
-   - If nothing changed: report "Merge risk assessment up to date" and stop.
-   - Update only the affected risk categories. Preserve manually-added risk indicators in unchanged categories.
-   - If changes are pervasive, fall back to Generate mode.
-
-3. **Extract risk indicators**
-
-   From the documents and code analysis, extract concrete, testable risk indicators. Follow the [category reference](category-reference.md) for the full list of categories, indicator quality standards, and the skill file template.
-
-   Each risk indicator must identify a code path or change pattern that, when touched, makes a PR too dangerous to auto-merge. The indicator must be something an AI agent can detect by reading the PR diff.
-
-4. **Write the skill**
-
-   Write (or update) `.agents/skills/pc-merge-risk-assess/SKILL.md` using the template from the [category reference](category-reference.md). Only include sections that have real indicators. Omit empty sections.
-
-5. **Update agents**
-
-   For every `*-engineer.md` in `.opencode/agents/`, add `@pc-merge-risk-assess` to the Agent Workflow ability group (skip if already present). This ensures every engineer can evaluate risk before merge. Use this pattern:
-   ```markdown
-   ## Abilities
-   - Guardrails: @pc-guardrails-generic, @pc-guardrails-project[, ...existing entries unchanged]
-   ...
-   - Development, Agent Workflow: @pc-merge-risk-assess[, ...existing entries unchanged]
-   ```
-
-   If no "Development, Agent Workflow" line exists, create it. Exclude tier variant files (`*-engineer.build.md`, `*-engineer.fast.md`, `*-engineer.plan.md`): they are generated copies; only update the base templates.
-
-6. **Report**
-
-   Tell the user:
-   - Whether the skill was generated or updated (and which categories changed)
-   - Number of risk indicators extracted per category
-   - Number of agent files updated
-   - Tip: "Rerun `/make-merge-risk-assess` any time the architecture or project guardrails change significantly."
+---
+name: pc-make-merge-risk-assess
+description: Generate or update the pc-merge-risk-assess skill from project guardrails and architecture. Produces a PR-level risk assessment that loop recipes can gate automerge on. Invoked by the /make-merge-risk-assess command and the repo-initialize flow.
+license: MIT
+---
+
+# Make Merge Risk Assess
+
+Analyze `ARCHITECTURE.md`, the project guardrails skill, and other project files to generate or update an `pc-merge-risk-assess` skill: a checklist of risk indicators that an AI agent evaluates before auto-merging a pull request. When any indicator matches, the agent blocks automerge and leaves the PR for human review with an explanation.
+
+## Steps
+
+1. **Check current state**
+
+   Read `.agents/skills/pc-merge-risk-assess/SKILL.md`. Determine which mode to use:
+   - Does not exist: Generate mode. Create from scratch.
+   - Exists and has a `<!-- Last updated:` footer: Update mode. Incrementally update.
+   - Exists but no timestamp: proceed in Generate mode (full regeneration).
+
+2a. **Generate mode: read source documents**
+
+   Read ALL of the following that exist:
+   - `.agents/skills/pc-guardrails-project/SKILL.md` (primary source — project-specific constraints)
+   - `.agents/skills/pc-guardrails-generic/SKILL.md` (generic safety rules)
+   - `ARCHITECTURE.md` (architecture boundaries, critical paths)
+   - `AGENTS.md` (non-negotiable constraints, verification rules)
+   - `.opencode/harness.json` (platform, concurrency)
+   - CI/CD workflows: `.github/workflows/*`, `azure-pipelines.yml`: whatever exists
+   - Loop recipes: `.loops/recipes/*-loop.yaml` (understand the automerge flow)
+
+   Use file tools to discover risk-critical code paths: `grep` for calculation engines, audit appenders, auth middleware, schema migrations, permission checks, and other sensitive areas.
+
+2b. **Update mode: incremental analysis**
+
+   Extract the `<!-- Last updated: <ISO date> -->` timestamp from the existing skill file. Then:
+   - Read `.agents/skills/pc-guardrails-project/SKILL.md` and check its `<!-- Last updated:` timestamp. If the guardrails haven't changed and ARCHITECTURE.md hasn't changed since the risk skill was last generated, report "Merge risk assessment up to date" and stop.
+   - Run `git log --oneline --since="<date>" -- <relevant config and architecture files>` to find what changed.
+   - If nothing changed: report "Merge risk assessment up to date" and stop.
+   - Update only the affected risk categories. Preserve manually-added risk indicators in unchanged categories.
+   - If changes are pervasive, fall back to Generate mode.
+
+3. **Extract risk indicators**
+
+   From the documents and code analysis, extract concrete, testable risk indicators. Follow the [category reference](category-reference.md) for the full list of categories, indicator quality standards, and the skill file template.
+
+   Each risk indicator must identify a code path or change pattern that, when touched, makes a PR too dangerous to auto-merge. The indicator must be something an AI agent can detect by reading the PR diff.
+
+4. **Write the skill**
+
+   Write (or update) `.agents/skills/pc-merge-risk-assess/SKILL.md` using the template from the [category reference](category-reference.md). Only include sections that have real indicators. Omit empty sections.
+
+5. **Update agents**
+
+   For every `*-engineer.md` in `.opencode/agents/`, add `@pc-merge-risk-assess` to the Agent Workflow ability group (skip if already present). This ensures every engineer can evaluate risk before merge. Use this pattern:
+   ```markdown
+   ## Abilities
+   - Guardrails: @pc-guardrails-generic, @pc-guardrails-project[, ...existing entries unchanged]
+   ...
+   - Development, Agent Workflow: @pc-merge-risk-assess[, ...existing entries unchanged]
+   ```
+
+   If no "Development, Agent Workflow" line exists, create it. Exclude tier variant files (`*-engineer.build.md`, `*-engineer.fast.md`, `*-engineer.plan.md`): they are generated copies; only update the base templates.
+
+6. **Report**
+
+   Tell the user:
+   - Whether the skill was generated or updated (and which categories changed)
+   - Number of risk indicators extracted per category
+   - Number of agent files updated
+   - Tip: "Rerun `/make-merge-risk-assess` any time the architecture or project guardrails change significantly."

package/skills/pc-make-merge-risk-assess/category-reference.md

@@ -1,114 +1,114 @@
-# Merge risk assessment category reference
-
-From the project guardrails, architecture, and code analysis, extract concrete, testable risk indicators in these categories. Only include a category if you found real evidence for it.
-
-- **Calculation integrity**: changes to whatever this project computes and cannot get wrong — an engine, its formula inputs, its reference tables, its assumptions. Any file under that namespace is an indicator. See the worked example below for the shape.
-- **Audit & compliance**: modifications to audit appenders, audit log storage, hash-chaining, or tamper-evident mechanisms. Any change that could affect regulatory traceability.
-- **Authentication & authorization**: changes to auth middleware, permission checks, role definitions, token issuance, or session management. Changes to `.RequirePermission()` calls or permission seed data.
-- **Data schema & migration**: EF Core entity changes, new migrations, column type changes, constraint additions/removals, or seed data modifications. Schema changes are always risky because they affect production data.
-- **Reference data versioning**: changes to effective-dated configuration, rate or band tables, assumptions, or any constant an output depends on. Changes to versioning or snapshot logic.
-- **Cross-boundary violations**: imports that break the layering direction (e.g. Domain referencing Application, Application referencing ASP.NET), cross-context data access bypassing ports.
-- **Security surface**: new endpoints without authorization, input validation removal, secrets exposure, dependency version downgrades, or changes to security scanning configuration.
-- **Financial correctness**: where the project handles money, any change that could produce a wrong amount — tax, currency, precision, rounding, or the type money is stored in.
-- **State machine transitions**: modifications to entity lifecycle transitions (e.g. quote status flow, approval gates, sign-off logic). Breaking a state machine can leave data in unrecoverable states.
-- **Integration contracts**: changes to external API contracts, webhook payloads, or CRM integration ports. Breaking integrations can cascade to downstream systems.
-
-Each indicator must be:
-
-- **Concrete**: name the type, method or path — "Changes to `OrderTotal.Calculate`" not "Changes to important calculations".
-- **Evidence-based**: derived from the project guardrails, the architecture, and actual code paths.
-- **Detectable**: findable by reading the PR diff alone — file paths, class names, method names, import changes.
-- **Exclusive**: each indicator belongs to one category. Never repeat it in a second.
-- **Not enforced elsewhere.** Skip anything CI already fails the build on. An indicator that duplicates a required check adds a human review the pipeline did not need.
-
-**At most 40 indicators, across all categories.** Rank by what a missed regression costs and cut from the bottom. A file this size is read on every merge decision, and past roughly this many, compliance drops regardless of how good each line is — so an indicator that will not change a verdict is worse than absent.
-
-## Worked example
-
-One project's calculation-integrity indicator, for shape only. Replace it with this repository's own: edits between the `PC-PROJECT-EXAMPLE` markers are carried over when the harness updates, and anything outside them is replaced by the shipped version.
-
-<!-- PC-PROJECT-EXAMPLE-START -->
-```markdown
-### Calculation Integrity
-- Any change under `src/pricing/engine/` — `RateEngine.Compute` is static and deterministic, and every change to it needs a golden vector in `PricingParityTests`. A wrong number here is invisible in review and correct-looking in production.
-- Any change to a rate table, band, or assumption constant, including its effective dates. The engine reads them by date, so an edit silently rewrites past outputs.
-```
-<!-- PC-PROJECT-EXAMPLE-END -->
-
-## Skill template
-
-Write (or update) `.agents/skills/pc-merge-risk-assess/SKILL.md`:
-
-```markdown
----
-name: pc-merge-risk-assess
-description: Evaluate a pull request for merge risk. Load when a loop recipe or agent needs to decide whether a PR is safe to auto-merge or requires human review. Produces a structured risk assessment with a binary outcome and reasoning.
-license: MIT
----
-
-# Merge Risk Assessment
-
-> Auto-generated by `/make-merge-risk-assess`. Regenerate when architecture or guardrails change.
-
-## Purpose
-
-Determine whether a pull request is safe to auto-merge or requires human review. This skill is loaded by AI agents in loop recipes (e.g. `dev-assess-risk`) before merging. The agent inspects the PR diff and evaluates each risk indicator below.
-
-## Output contract
-
-On completion, produce a single JSON object on stdout:
-
-```json
-{"riskLevel":"safe"|"risky","reason":"<one-sentence explanation if risky, or 'No risk indicators detected' if safe>"}
-```
-
-- `riskLevel: "risky"` → exit non-zero. The loop recipe routes to the "leave for human review" path.
-- `riskLevel: "safe"` → exit zero. The loop recipe routes to the automerge path.
-
-## Risk indicators
-
-### Calculation Integrity
-- <indicator: file path, class, or method pattern>
-- <indicator>
-
-### Audit & Compliance
-- <indicator>
-
-### Authentication & Authorization
-- <indicator>
-
-### Data Schema & Migration
-- <indicator>
-
-### Reference Data Versioning
-- <indicator>
-
-### Cross-Boundary Violations
-- <indicator>
-
-### Security Surface
-- <indicator>
-
-### Financial Correctness
-- <indicator>
-
-### State Machine Transitions
-- <indicator>
-
-### Integration Contracts
-- <indicator>
-
-## Evaluation rules
-
-1. **Load `@pc-guardrails-project` first.** Every non-negotiable constraint in the project guardrails is a potential risk indicator. If a change violates or weakens any guardrail, the outcome is `risky`.
-2. **Inspect the full PR diff** using `gh pr diff <url>`. Do not guess based on the PR title or description alone.
-3. **Check each risk indicator** against the diff. A single matching indicator is sufficient to flag as `risky`.
-4. **When risky, explain why.** The `reason` field must name the specific indicator that matched and the files involved. Do not give vague explanations.
-5. **Do not second-guess the developer.** If the changes look intentional and no indicator matches, classify as `safe`. The purpose is to catch dangerous changes, not to block all non-trivial work.
-6. **Pure additions are lower risk.** New files, new endpoints with authorization, new tests, new UI components that don't touch existing critical paths are generally safe unless they introduce schema changes or cross-boundary imports.
-7. **Refactors within a single layer are generally safe.** Renaming, extracting methods, or reorganizing within the same bounded context and same architectural layer rarely triggers a risk indicator unless the refactor changes behavior.
-
-<!-- Last updated: <current ISO timestamp> -->
-```
-
-Only include sections that have real indicators. Omit empty sections and their headers.
+# Merge risk assessment category reference
+
+From the project guardrails, architecture, and code analysis, extract concrete, testable risk indicators in these categories. Only include a category if you found real evidence for it.
+
+- **Calculation integrity**: changes to whatever this project computes and cannot get wrong — an engine, its formula inputs, its reference tables, its assumptions. Any file under that namespace is an indicator. See the worked example below for the shape.
+- **Audit & compliance**: modifications to audit appenders, audit log storage, hash-chaining, or tamper-evident mechanisms. Any change that could affect regulatory traceability.
+- **Authentication & authorization**: changes to auth middleware, permission checks, role definitions, token issuance, or session management. Changes to `.RequirePermission()` calls or permission seed data.
+- **Data schema & migration**: EF Core entity changes, new migrations, column type changes, constraint additions/removals, or seed data modifications. Schema changes are always risky because they affect production data.
+- **Reference data versioning**: changes to effective-dated configuration, rate or band tables, assumptions, or any constant an output depends on. Changes to versioning or snapshot logic.
+- **Cross-boundary violations**: imports that break the layering direction (e.g. Domain referencing Application, Application referencing ASP.NET), cross-context data access bypassing ports.
+- **Security surface**: new endpoints without authorization, input validation removal, secrets exposure, dependency version downgrades, or changes to security scanning configuration.
+- **Financial correctness**: where the project handles money, any change that could produce a wrong amount — tax, currency, precision, rounding, or the type money is stored in.
+- **State machine transitions**: modifications to entity lifecycle transitions (e.g. quote status flow, approval gates, sign-off logic). Breaking a state machine can leave data in unrecoverable states.
+- **Integration contracts**: changes to external API contracts, webhook payloads, or CRM integration ports. Breaking integrations can cascade to downstream systems.
+
+Each indicator must be:
+
+- **Concrete**: name the type, method or path — "Changes to `OrderTotal.Calculate`" not "Changes to important calculations".
+- **Evidence-based**: derived from the project guardrails, the architecture, and actual code paths.
+- **Detectable**: findable by reading the PR diff alone — file paths, class names, method names, import changes.
+- **Exclusive**: each indicator belongs to one category. Never repeat it in a second.
+- **Not enforced elsewhere.** Skip anything CI already fails the build on. An indicator that duplicates a required check adds a human review the pipeline did not need.
+
+**At most 40 indicators, across all categories.** Rank by what a missed regression costs and cut from the bottom. A file this size is read on every merge decision, and past roughly this many, compliance drops regardless of how good each line is — so an indicator that will not change a verdict is worse than absent.
+
+## Worked example
+
+One project's calculation-integrity indicator, for shape only. Replace it with this repository's own: edits between the `PC-PROJECT-EXAMPLE` markers are carried over when the harness updates, and anything outside them is replaced by the shipped version.
+
+<!-- PC-PROJECT-EXAMPLE-START -->
+```markdown
+### Calculation Integrity
+- Any change under `src/pricing/engine/` — `RateEngine.Compute` is static and deterministic, and every change to it needs a golden vector in `PricingParityTests`. A wrong number here is invisible in review and correct-looking in production.
+- Any change to a rate table, band, or assumption constant, including its effective dates. The engine reads them by date, so an edit silently rewrites past outputs.
+```
+<!-- PC-PROJECT-EXAMPLE-END -->
+
+## Skill template
+
+Write (or update) `.agents/skills/pc-merge-risk-assess/SKILL.md`:
+
+```markdown
+---
+name: pc-merge-risk-assess
+description: Evaluate a pull request for merge risk. Load when a loop recipe or agent needs to decide whether a PR is safe to auto-merge or requires human review. Produces a structured risk assessment with a binary outcome and reasoning.
+license: MIT
+---
+
+# Merge Risk Assessment
+
+> Auto-generated by `/make-merge-risk-assess`. Regenerate when architecture or guardrails change.
+
+## Purpose
+
+Determine whether a pull request is safe to auto-merge or requires human review. This skill is loaded by AI agents in loop recipes (e.g. `dev-assess-risk`) before merging. The agent inspects the PR diff and evaluates each risk indicator below.
+
+## Output contract
+
+On completion, produce a single JSON object on stdout:
+
+```json
+{"riskLevel":"safe"|"risky","reason":"<one-sentence explanation if risky, or 'No risk indicators detected' if safe>"}
+```
+
+- `riskLevel: "risky"` → exit non-zero. The loop recipe routes to the "leave for human review" path.
+- `riskLevel: "safe"` → exit zero. The loop recipe routes to the automerge path.
+
+## Risk indicators
+
+### Calculation Integrity
+- <indicator: file path, class, or method pattern>
+- <indicator>
+
+### Audit & Compliance
+- <indicator>
+
+### Authentication & Authorization
+- <indicator>
+
+### Data Schema & Migration
+- <indicator>
+
+### Reference Data Versioning
+- <indicator>
+
+### Cross-Boundary Violations
+- <indicator>
+
+### Security Surface
+- <indicator>
+
+### Financial Correctness
+- <indicator>
+
+### State Machine Transitions
+- <indicator>
+
+### Integration Contracts
+- <indicator>
+
+## Evaluation rules
+
+1. **Load `@pc-guardrails-project` first.** Every non-negotiable constraint in the project guardrails is a potential risk indicator. If a change violates or weakens any guardrail, the outcome is `risky`.
+2. **Inspect the full PR diff** using `gh pr diff <url>`. Do not guess based on the PR title or description alone.
+3. **Check each risk indicator** against the diff. A single matching indicator is sufficient to flag as `risky`.
+4. **When risky, explain why.** The `reason` field must name the specific indicator that matched and the files involved. Do not give vague explanations.
+5. **Do not second-guess the developer.** If the changes look intentional and no indicator matches, classify as `safe`. The purpose is to catch dangerous changes, not to block all non-trivial work.
+6. **Pure additions are lower risk.** New files, new endpoints with authorization, new tests, new UI components that don't touch existing critical paths are generally safe unless they introduce schema changes or cross-boundary imports.
+7. **Refactors within a single layer are generally safe.** Renaming, extracting methods, or reorganizing within the same bounded context and same architectural layer rarely triggers a risk indicator unless the refactor changes behavior.
+
+<!-- Last updated: <current ISO timestamp> -->
+```
+
+Only include sections that have real indicators. Omit empty sections and their headers.