@daochild/agents-config 2.1.0 → 2.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
@@ -4,6 +4,7 @@
4
4
 
5
5
  - Read `AGENTS.md` before making changes. It is the repository's primary instruction source; use `ARCHITECTURE.md`, `CONTRIBUTING.md`, and `SECURITY.md` for the relevant architectural, contribution, and security details.
6
6
  - This is the npm package `@daochild/agents-config`, not an application. OpenCode-facing agent, command, rule, and skill sources live under `instructions/`; `opencode.json` declares the paths used by OpenCode. Client-specific counterparts may be maintained under `.claude/` and `.agents/`.
7
+ - Landing a new skill under `instructions/skills/` requires NVIDIA Skillspector per `instructions/rules/nvidia-skillspector-check.md` and `CONTRIBUTING.md`; local-only `npx skills` installs outside this repo do not.
7
8
  - Before changing an agent component, inspect the actual file paths and matching `opencode.json` entry. Some agent prompts and always-on instruction entries may still use legacy client-specific paths; align them with the source under `instructions/` when modifying those registrations. Follow `CONTRIBUTING.md` for counterpart formats and checks.
8
9
  - Treat the SDLC gate order and risk/autonomy rules as controls, not optional workflow suggestions. Classify risk before implementation; use the orchestrator for multi-component or medium/high-risk work. The author of a change must not be its sole reviewer, and high-risk approval decisions belong to a human.
9
10
  - Configuration and prompt text do not enforce authorization or isolate tools. Runtime hosts must enforce permissions and approvals at side-effect boundaries.
package/AGENTS.md CHANGED
@@ -29,8 +29,8 @@ Instructions:
29
29
  ## Audit Rule
30
30
 
31
31
  When the current task involves significant code changes — for example, after the first code-generation prompt or after
32
- substantial deviations from the agreed Statement of Work (SOW) — the agent MUST run a system audit before finalizing the
33
- output.
32
+ substantial deviations from the agreed statement of work (requirement/PRD artifacts; `SOW.md` was superseded by the
33
+ `sdlc-regulatory` skill) — the agent MUST run a system audit before finalizing the output.
34
34
 
35
35
  1. **Pick the right auditor skill** for the domain of the change. Examples (replace `xxx` with the actual domain):
36
36
  - Smart contracts / EVM → `senior-solidity-auditor`
@@ -39,9 +39,8 @@ output.
39
39
  - General architecture / system design → `senior-software-architect`
40
40
  2. **Run the audit via the matching `xxx-auditor` skill.** Surface findings, severity, and concrete remediation steps.
41
41
  3. **If the required skill does not exist locally, create it first:**
42
- - Add `instructions/skills/<xxx-auditor>/SKILL.md`
43
- - Mirror to `.claude/skills/<xxx-auditor>/SKILL.md` when a Claude Code counterpart is maintained
44
- - Register the skill path in `opencode.json` if needed
42
+ - Add `instructions/skills/<xxx-auditor>/SKILL.md` — auto-discovered via `skills.paths`, no `opencode.json` edit needed
43
+ - Add `.claude/` / `.agents/` counterparts only when that client is in scope (see `CONTRIBUTING.md`)
45
44
  - Then execute the audit using the newly created skill.
46
45
 
47
46
  Do not skip the audit because a skill is missing; create the skill and perform the audit as part of the same session.
@@ -54,13 +53,16 @@ for any feature/change that touches multiple modules or is medium/high risk.
54
53
 
55
54
  ### Components
56
55
 
57
- | Component | Path (opencode) | Claude mirror | Agent Skills mirror |
58
- |-----------------------|--------------------------------------------------------------------------------------|------------------------------------------------|-------------------------------------------|
59
- | Methodology skill | `instructions/skills/sdlc-regulatory/SKILL.md` | `.claude/skills/sdlc-regulatory/SKILL.md` | `.agents/skills/sdlc-regulatory/SKILL.md` |
60
- | Always-on rule | `instructions/rules/sdlc-gates.md` (register in `opencode.json`) | `.claude/rules/sdlc-gates.md` | `.agents/rules/sdlc-gates.md` |
61
- | Orchestrator subagent | `instructions/agent/sdlc-orchestrator.md` | `.claude/agents/sdlc-orchestrator.md` | `.agents/agents/sdlc-orchestrator.md` |
62
- | Role subagents (×9) | `instructions/agent/sdlc-{analyst,pm,architect,sm,dev,qa,security,reviewer,auditor}.md` | mirrored (Claude Code frontmatter, no `mode:`) | mirrored verbatim |
63
- | `/sdlc` slash command | `instructions/command/sdlc.md` | `.claude/commands/sdlc.md` | `.agents/commands/sdlc.md` |
56
+ | Component | Path | OpenCode registration |
57
+ |-----------------------|---------------------------------------------------------------------|----------------------------|
58
+ | Methodology skill | `instructions/skills/sdlc-regulatory/SKILL.md` | auto via `skills.paths` |
59
+ | Always-on rule | `instructions/rules/sdlc-gates.md` | `instructions` array |
60
+ | Orchestrator subagent | `instructions/agent/sdlc-orchestrator.md` | `agent` + `command.sdlc` |
61
+ | Role subagents (×9) | `instructions/agent/sdlc-{analyst,pm,architect,sm,dev,qa,security,reviewer,auditor}.md` | `agent` entries |
62
+ | `/sdlc` slash command | `instructions/command/sdlc.md` | `command.sdlc.template` |
63
+
64
+ No `.claude/` or `.agents/` mirrors exist for these today; create counterparts only when another client is in scope
65
+ (see `CONTRIBUTING.md`).
64
66
 
65
67
  ### SDLC chain
66
68
 
@@ -92,50 +94,86 @@ plugins, or commands.
92
94
 
93
95
  ```
94
96
  agents-config/
95
- ├── AGENTS.md # Repo-level layout + cross-tool conventions
96
- ├── opencode.json # opencode project config (schema-pinned)
97
- ├── LICENSE
98
- ├── docs/ # Project documentation
99
- ├── instructions/ # OpenCode-facing agents, commands, rules, and skills
100
- │ ├── agent/
101
- │ ├── command/
102
- │ ├── rules/
103
- │ └── skills/
97
+ ├── AGENTS.md / ARCHITECTURE.md / CONTRIBUTING.md / README.md / SECURITY.md
98
+ ├── CLAUDE.md # Claude Code entry: @AGENTS.md
99
+ ├── opencode.json # instructions, skills.paths, commands, agents (schema-pinned)
100
+ ├── package.json # scripts: test, sdlc:check, postinstall
101
+ ├── skills-lock.json # provenance for externally sourced skills
102
+ ├── instructions/ # OpenCode-facing sources — the real component tree
103
+ │ ├── agent/ # subagent prompts (sdlc-*, harness-*, docs)
104
+ │ ├── command/ # slash-command templates (sdlc, harness)
105
+ │ ├── rules/ # always-on rules (sdlc-gates, harness-engineering, nvidia-skillspector-check)
106
+ │ └── skills/ # first-party skills (auto-discovered)
107
+ ├── .agents/skills/security-audit/ # external skill (ADR 0003), not in skills.paths
108
+ ├── scripts/ # postinstall.js, sdlc-session-check.js
109
+ ├── test/ # node --test suites, incl. opencode.json path validation
110
+ ├── .github/copilot-instructions.md
111
+ └── docs/ # BUSINESS_LOGIC, IMPLEMENTATION, adr/, stories/, ...
104
112
  ```
105
113
 
106
114
  ## Linking
107
115
 
108
- OpenCode-facing content is organized under `instructions/` and loaded through
109
- `opencode.json`. Keep configured paths aligned with the actual files; create
110
- client-specific counterparts only for clients the component must support.
116
+ - OpenCode loads `opencode.json` → `instructions`: `AGENTS.md` plus three always-on rules
117
+ (`instructions/rules/sdlc-gates.md`, `instructions/rules/harness-engineering.md`,
118
+ `instructions/rules/nvidia-skillspector-check.md`). Skills are discovered only from `skills.paths` →
119
+ `instructions/skills`.
120
+ - Every `agent.*.prompt`, `command.*.template`, and `instructions` entry is a real path that `npm test` verifies —
121
+ if you move or rename a file under `instructions/`, update `opencode.json` in the same change.
122
+ - Claude Code reads root `CLAUDE.md` (`@AGENTS.md`); Copilot reads `.github/copilot-instructions.md`.
123
+ - `.agents/skills/security-audit/` is an externally sourced skill (provenance in `skills-lock.json`, ADR 0003); it is
124
+ deliberately NOT in `skills.paths`.
125
+ - Config loads once at startup — restart OpenCode after editing `opencode.json` or any file under `instructions/`.
126
+
127
+ ## Commands
128
+
129
+ - `npm test` — runs `node --test` over `test/` (no framework config; includes `agent-config.test.js`, which fails if
130
+ any `opencode.json` path points at a missing file). Run this after every config/path change.
131
+ - `node --test --test-name-pattern="<name>" test/<file>.test.js` — run a single test.
132
+ - `npm run sdlc:check [-- --model provider/model]` — read-only SDLC session diagnostic; needs the OpenCode CLI and an
133
+ authenticated provider (see `README.md`).
134
+ - There is no lint/typecheck/build step — this package ships Markdown + JSON only.
111
135
 
112
136
  ## Adding a new component
113
137
 
114
- | Component | opencode path | Claude Code path | Agent Skills path |
115
- |----------------|---------------------------------------|-------------------------------|-------------------------------|
116
- | Subagent | `instructions/agent/<n>.md` | `.claude/agents/<n>.md` | `.agents/agents/<n>.md` |
117
- | Skill | `instructions/skills/<n>/SKILL.md` | `.claude/skills/<n>/SKILL.md` | `.agents/skills/<n>/SKILL.md` |
118
- | Slash command | `instructions/command/<n>.md` | `.claude/commands/<n>.md` | `.agents/commands/<n>.md` |
119
- | Plugin | `plugin/<n>.ts` | n/a | n/a |
120
- | Always-on rule | `instructions/rules/<n>.md`, register in `opencode.json` | `.claude/rules/<n>.md` | `.agents/rules/<n>.md` |
138
+ Add OpenCode-facing components under `instructions/` and register them in `opencode.json` where required
139
+ (CONTRIBUTING.md has the full workflow, mirror rules, and frontmatter differences):
140
+
141
+ | Component | Path | Registered in `opencode.json` |
142
+ |----------------|-------------------------------------|------------------------------------------------|
143
+ | Subagent | `instructions/agent/<n>.md` | `agent.<n>.prompt` = `{file:./instructions/agent/<n>.md}` |
144
+ | Skill | `instructions/skills/<n>/SKILL.md` | nothing — auto-discovered via `skills.paths` |
145
+ | Slash command | `instructions/command/<n>.md` | `command.<n>.template` = `{file:./instructions/command/<n>.md}` |
146
+ | Always-on rule | `instructions/rules/<n>.md` | append to `instructions` array |
147
+ | Plugin | `plugin/<n>.ts` | `plugin` array (no plugins exist yet) |
148
+
149
+ `.claude/` and `.agents/` counterparts are optional and currently absent; create them only for clients in scope.
150
+
151
+ When adding a skill under `instructions/skills/`, follow `instructions/rules/nvidia-skillspector-check.md`: run NVIDIA
152
+ Skillspector on the skill, resolve reported issues, and attach approval artifacts to the PR. The rule is always-on for
153
+ OpenCode; it does not apply to end-user installs via `npx skills` outside this repository. Record external skills in
154
+ `skills-lock.json` when they are not on `skills.paths` (see `.agents/skills/security-audit/`).
121
155
 
122
156
  ## Harness engineering
123
157
 
124
- The `harness-engineering` rule and skill under `instructions/` provide guidance
125
- for reliable agent workflows. Maintain client-specific counterparts when needed. Load the skill when designing or changing agent context,
158
+ The `harness-engineering` rule (`instructions/rules/harness-engineering.md`, always-on) and skill
159
+ (`instructions/skills/harness-engineering/SKILL.md`) provide shared guidance
160
+ for reliable agent workflows. The `/harness` command runs `harness-orchestrator`, which delegates only to
161
+ `general`, `sdlc-orchestrator`, and the read-only `harness-verifier`; `experimental.subagent_depth: 3` is what allows
162
+ harness → SDLC → role nesting. Load the skill when designing or changing agent context,
126
163
  tools, permissions, approvals, verification, or telemetry. The consuming agent host—not
127
164
  these configuration files—must enforce authorization, isolation, approvals, and runtime
128
- limits.
165
+ limits. These properties are pinned by `test/agent-config.test.js`.
129
166
 
130
167
  ## Code Generation Pipeline
131
168
 
132
169
  To create an agent for code generation tasks:
133
170
 
134
- 1. **Define the agent** in `instructions/agent/code-generator.md`:
171
+ 1. **Define the agent** in `instructions/agent/code-generator.md` (use `mode: subagent` — `test/agent-config.test.js`
172
+ asserts every agent registered in `opencode.json` uses it):
135
173
  ```markdown
136
174
  ---
137
175
  description: Generates code based on specifications and requirements
138
- mode: primary
176
+ mode: subagent
139
177
  model: anthropic/claude-sonnet-4-6
140
178
  permission:
141
179
  edit: ask
@@ -145,7 +183,7 @@ To create an agent for code generation tasks:
145
183
  You are a code generation agent specialized in creating high-quality code...
146
184
  ```
147
185
 
148
- 2. **Create supporting rules** in `.claude/rules/code-generation.md`:
186
+ 2. **Create supporting rules** in `instructions/rules/code-generation.md` and register them in the `opencode.json` `instructions` array:
149
187
  - Coding standards and patterns
150
188
  - Language-specific guidelines
151
189
  - Testing requirements
@@ -328,7 +366,7 @@ At the end of each session or task, review and update relevant documentation:
328
366
 
329
367
  ### Documentation Checklist (End of Session)
330
368
 
331
- - [ ] New files/directories documented in appropriate README or STRUCTURE.md
369
+ - [ ] New files/directories documented in appropriate README or ARCHITECTURE.md
332
370
  - [ ] Architecture decisions recorded in ADRs or ARCHITECTURE.md
333
371
  - [ ] API changes reflected in documentation
334
372
  - [ ] Configuration changes documented
package/CONTRIBUTING.md CHANGED
@@ -29,6 +29,21 @@ client.
29
29
  | Plugin | `plugin/<n>.ts` | n/a | n/a |
30
30
  | Always-on rule | `instructions/rules/<n>.md` | `.claude/rules/<n>.md` | `.agents/rules/<n>.md` |
31
31
 
32
+ ### Adding a skill to this repository
33
+
34
+ Installing a skill with `npx skills` on a developer machine is separate from **landing** a skill in `agents-config`.
35
+ Before you add or update `instructions/skills/<n>/SKILL.md` (and any `.claude/` / `.agents/` mirrors), comply with
36
+ `instructions/rules/nvidia-skillspector-check.md`:
37
+
38
+ 1. Run NVIDIA Skillspector on the skill source and fix compliance, security, or compatibility findings.
39
+ 2. Pass the SDLC Implementation Gate when the change is medium/high risk or spans multiple components (`/sdlc`).
40
+ 3. Add the skill under `instructions/skills/<n>/SKILL.md` — no `opencode.json` entry needed beyond `skills.paths`.
41
+ 4. Put Skillspector reports or approval artifacts in the PR description.
42
+ 5. Update `skills-lock.json` when the skill is externally sourced and not on `skills.paths`.
43
+
44
+ Use the `find-skills` skill to discover candidates from the open ecosystem; always complete Skillspector before merging
45
+ into this repo.
46
+
32
47
  ### Format differences
33
48
 
34
49
  - **opencode subagent frontmatter** uses `mode: subagent` (and optional `permission`).
package/README.md CHANGED
@@ -7,9 +7,9 @@ The package is intended for production‑grade automation: version control, CI/C
7
7
  ## What's in the box
8
8
 
9
9
  - **Shared layout & conventions** — `AGENTS.md` is the single source of truth, inherited (not copied) by consuming projects.
10
- - **Shared instruction sources** — OpenCode-facing agents, commands, rules, and skills are organized under `instructions/`; `opencode.json` declares the paths used by OpenCode. Keep configured paths aligned with the files and maintain Claude Code or Agent Skills counterparts when required; see `AGENTS.md` and `CONTRIBUTING.md`.
10
+ - **Shared instruction sources** — OpenCode-facing agents, commands, rules, and skills are organized under `instructions/`; `opencode.json` declares the paths used by OpenCode. Keep configured paths aligned with the files and maintain Claude Code or Agent Skills counterparts when required; see `AGENTS.md` and `CONTRIBUTING.md`. New skills under `instructions/skills/` require NVIDIA Skillspector approval per `instructions/rules/nvidia-skillspector-check.md` (see `CONTRIBUTING.md`).
11
11
  - **AI-Driven SDLC framework** — `sdlc-regulatory` skill + 10 `sdlc-*` subagents + `sdlc-gates` rule + `/sdlc` command. Gates run in order (requirement → architecture → implementation → testing → security → review → deployment → DoD), AI never self-validates, high-risk changes require human approval, and a compliance crosswalk covers EU AI Act / NIST AI RMF / ISO 42001 / SOC 2 / GDPR.
12
- - **Domain skills** — `senior-qa`, `senior-solidity-auditor`, `senior-bitcoin-auditor`, `senior-frontend-dev`, `senior-software-developer`, `senior-ux-ui-designer`, `archivarius`, `data-engineer`, `find-skills`, `frontend-design`.
12
+ - **Domain skills** — `senior-qa`, `senior-solidity-auditor`, `senior-bitcoin-auditor`, `senior-frontend-dev`, `senior-software-developer`, `senior-ux-ui-designer`, `archivarius`, `data-engineer`, `find-skills`, `frontend-design`, `grill-me`.
13
13
  - **Externally sourced skill** — `security-audit` is maintained at `.agents/skills/security-audit/` and sourced from `cloudflare/security-audit-skill`. Its source and computed hash are recorded in `skills-lock.json`. It follows the Agent Skills layout and is separate from OpenCode's `instructions/skills` discovery path.
14
14
  - **Always-on rules** — `programming-best-practices` and `sdlc-gates`.
15
15
  - **AI-readable contract** — `ARCHITECTURE.md`, `CONTRIBUTING.md`, `SECURITY.md`, `docs/` (business logic, implementation status, ADRs).
@@ -23,7 +23,7 @@ The SDLC regulatory framework was added in the current cycle and is the most rec
23
23
  | SDLC orchestrator | Done | `instructions/agent/sdlc-orchestrator.md` | Entry point for `/sdlc` |
24
24
  | SDLC role subagents (×9) | Done | `instructions/agent/sdlc-{analyst,pm,architect,sm,dev,qa,security,reviewer,auditor}.md` | One per gate |
25
25
  | `/sdlc` command | Done | `instructions/command/sdlc.md` | Invokes orchestrator |
26
- | Domain skills | Done | `instructions/skills/{archivarius,data-engineer,find-skills,frontend-design,harness-engineering,senior-bitcoin-auditor,senior-frontend-dev,senior-qa,senior-software-developer,senior-solidity-auditor,senior-ux-ui-designer}/` | Loaded on demand |
26
+ | Domain skills | Done | `instructions/skills/{archivarius,data-engineer,find-skills,frontend-design,grill-me,harness-engineering,senior-bitcoin-auditor,senior-frontend-dev,senior-qa,senior-software-developer,senior-solidity-auditor,senior-ux-ui-designer}/` | Loaded on demand |
27
27
  | External Agent Skill | Present | `.agents/skills/security-audit/SKILL.md`, `skills-lock.json` | Sourced from `cloudflare/security-audit-skill`; available through the Agent Skills layout, not OpenCode's `instructions/skills` path |
28
28
  | AI-readable contract files | Done | `ARCHITECTURE.md`, `CONTRIBUTING.md`, `SECURITY.md`, `docs/` | This cycle |
29
29
  | `index.js` entry | Stub | `package.json` → `main` | Placeholder; no runtime code yet |
@@ -76,6 +76,7 @@ limitations.
76
76
 
77
77
  | Date | Change | Author |
78
78
  |------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------------|
79
+ | 2026-11-12 | Bumped version to 2.2.0 (minor): NVIDIA Skillspector always-on rule and doc alignment; new `grill-me` skill; policy and skill-layout tests. | maintainer |
79
80
  | 2026-10-26 | Researched harness engineering sources, assessed the supplied six-component model, and documented a configuration-only implementation proposal. No runtime or agent configuration behavior changed; architecture approval is pending. | maintainer |
80
81
  | 2026-08-18 | Bumped version to 1.1.0 (minor) for the SDLC feature release; updated `package.json` description and keywords to reflect the SDLC/governance scope. | maintainer |
81
82
  | 2026-08-18 | Simplified `README.md` install section: collapsed "After installation" into "Installation"; replaced 3-line `AGENTS.md` block with a single pointer line. No contract change (no postinstall/bin; respects the "no runtime code" invariant). | maintainer |
@@ -0,0 +1,55 @@
1
+ # NVIDIA Skillspector Check (always-on)
2
+
3
+ > OpenCode-facing rule source: `instructions/rules/nvidia-skillspector-check.md`.
4
+
5
+ ## Mandatory skillspector verification before installation
6
+
7
+ Before installing any new skill in this repository, the skill MUST be checked against NVIDIA Skillspector. This is a mandatory verification step to ensure skills meet NVIDIA's standards for compatibility, security, and quality before being installed into the agents-config ecosystem.
8
+
9
+ ## Verification requirements
10
+
11
+ 1. **Skillspector pre-approval** - All new skills must be processed through NVIDIA Skillspector before installation
12
+ 2. **Compliance validation** - Skillspector must report:
13
+ - Compatibility with existing agent infrastructure
14
+ - No security vulnerabilities or compliance issues
15
+ - Adherence to NVIDIA's skill development guidelines
16
+ 3. **Documentation** - Skillspector reports or approval artifacts must be included with the installation PR
17
+
18
+ ## Implementation process
19
+
20
+ ### Phase 1: Preparation
21
+ - Verify Skillspector access is available for the skill author
22
+ - Prepare skill metadata, documentation, and test coverage
23
+ - Ensure skill follows all existing patterns in `instructions/skills/`
24
+
25
+ ### Phase 2: Skillspector validation
26
+ - Run NVIDIA Skillspector on the skill code
27
+ - Address any compliance, security, or compatibility issues
28
+ - Obtain Skillspector approval before proceeding
29
+
30
+ ### Phase 3: Installation
31
+ - Add `instructions/skills/<n>/SKILL.md` (auto-discovered via `skills.paths`; no per-skill `opencode.json` entry)
32
+ - Record externally sourced skills in `skills-lock.json` when they are not on `skills.paths`
33
+ - Use the `find-skills` skill to discover candidates; complete Skillspector before merging into this repo
34
+ - Update README or documentation as required
35
+
36
+ ## Error handling
37
+
38
+ If Skillspector validation fails:
39
+ - Block skill installation until compliance issues are resolved
40
+ - Document the specific failures in the PR
41
+ - Require Skillspector re-approval after fixes
42
+
43
+ ## Traceability
44
+
45
+ Skillspector validation results must be:
46
+ - Logged in the PR description
47
+ - Included as comments or artifacts in the repository
48
+ - Referenced in the DoD audit for skill-related changes
49
+
50
+ ## Related rules
51
+
52
+ This rule works in conjunction with:
53
+ - `sdlc-gates.md` - The Implementation Gate must be passed before skill installation
54
+ - `harness-engineering.md` - Must follow least-privilege principles and security validation
55
+ - `find-skills` skill (`instructions/skills/find-skills/SKILL.md`) - Discovery and install flow; repo land requires Skillspector (Step 4b)
@@ -71,6 +71,18 @@ For example:
71
71
  2. **Source reputation** — Official sources (`vercel-labs`, `anthropics`, `microsoft`) are more trustworthy than unknown authors.
72
72
  3. **GitHub stars** — Check the source repository. A skill from a repo with <100 stars should be treated with skepticism.
73
73
 
74
+ ### Step 4b: agents-config repository installs
75
+
76
+ When the user wants to **add a skill to the `agents-config` repo** (`instructions/skills/`), not only install it
77
+ locally with `npx skills`, follow `instructions/rules/nvidia-skillspector-check.md`:
78
+
79
+ 1. Run **NVIDIA Skillspector** on the skill and address failures before opening a PR.
80
+ 2. Add `instructions/skills/<n>/SKILL.md` (and `.claude/` / `.agents/` mirrors when those clients are in scope).
81
+ 3. Include Skillspector approval artifacts in the PR; update `skills-lock.json` for external skills off `skills.paths`.
82
+
83
+ Global `npx skills add` for a single developer does **not** require Skillspector unless they are contributing the
84
+ skill into `agents-config`.
85
+
74
86
  ### Step 5: Present Options to the User
75
87
 
76
88
  When you find relevant skills, present them to the user with:
@@ -95,7 +107,7 @@ Learn more: https://skills.sh/vercel-labs/agent-skills/react-best-practices
95
107
 
96
108
  ### Step 6: Offer to Install
97
109
 
98
- If the user wants to proceed, you can install the skill for them:
110
+ If the user wants a **local/global** install, you can install the skill for them:
99
111
 
100
112
  ```bash
101
113
  npx skills add <owner/repo@skill> -g -y
@@ -103,6 +115,9 @@ npx skills add <owner/repo@skill> -g -y
103
115
 
104
116
  The `-g` flag installs globally (user-level) and `-y` skips confirmation prompts.
105
117
 
118
+ If they want the skill **in agents-config**, use Step 4b (Skillspector + `instructions/skills/`) instead of only
119
+ running `npx skills add`.
120
+
106
121
  ## Common Skill Categories
107
122
 
108
123
  When searching, consider these common categories:
@@ -0,0 +1,148 @@
1
+ ---
2
+ name: grill-me
3
+ description: Adversarial accountability session that challenges both AI output and human operator choices—assumptions, evidence, skipped gates, and premature "done" claims. Use when the user asks to be grilled, red-teamed, stress-tested, or wants pushback before shipping, merging, or trusting a conclusion.
4
+ metadata:
5
+ scope: repo-level
6
+ version: "1.0"
7
+ ---
8
+
9
+ # Grill Me
10
+
11
+ Structured skepticism aimed at **two actors**:
12
+
13
+ 1. **The AI** — fluency, unverified claims, missing reads/tests, scope creep, false completion.
14
+ 2. **The operator** — vague intent, rubber-stamping, gate-skipping, urgency without criteria, trusting the model over evidence.
15
+
16
+ The tone is direct and forensic, not performative hostility. The goal is to surface what would **falsify** the current plan or "done" claim before irreversible action.
17
+
18
+ ## When to Use
19
+
20
+ Use `grill-me` when:
21
+
22
+ - The user says **grill me**, **challenge this**, **red team**, **what am I missing**, or **poke holes**.
23
+ - An agent claims **done**, **fixed**, or **ready to merge** without independent verification.
24
+ - A change skipped or compressed SDLC/harness steps (especially testing, security, or human review).
25
+ - Requirements or acceptance criteria were never written down.
26
+ - The operator and AI are aligned on a story but nobody has named risks or disconfirming evidence.
27
+
28
+ ## When NOT to Use
29
+
30
+ | Need | Use instead |
31
+ | --- | --- |
32
+ | Pick among ambiguous product/architecture options | `council` (if available) or explicit tradeoff analysis |
33
+ | Domain code/security audit | Matching `senior-*-auditor` or `security-audit` |
34
+ | Formal SDLC DoD sign-off | `sdlc-auditor` via `/sdlc` |
35
+ | Read-only check of harness artifacts | `harness-verifier` |
36
+ | Implementing fixes | Dev workflow; grill first, then implement |
37
+
38
+ ## Modes
39
+
40
+ | Mode | Duration | Use when |
41
+ | --- | --- | --- |
42
+ | **Flash grill** | ~5 questions | Quick sanity check before a small change |
43
+ | **Full grill** | Full worksheet below | Medium/high risk, production paths, or regulatory work |
44
+ | **Post-mortem grill** | After an incident | What did AI and operator each fail to verify? |
45
+
46
+ Default to **Flash** unless the user asks for depth or risk is medium/high per `sdlc-regulatory`.
47
+
48
+ ## Workflow
49
+
50
+ ### 1. Freeze the artifact
51
+
52
+ Write a short **claim ledger** (max 10 bullets):
53
+
54
+ - What the **AI** asserts (facts, estimates, opinions labeled per `AGENTS.md` honesty rules).
55
+ - What the **operator** decided (scope, shortcuts, approvals, overrides).
56
+ - Stated **acceptance criteria** (or explicit "none yet").
57
+
58
+ If criteria are missing, mark **BLOCKED** until the operator defines at least one observable pass/fail check.
59
+
60
+ ### 2. Dual-track interrogation
61
+
62
+ Run **both** tracks every time; do not let the AI hide behind the operator or vice versa.
63
+
64
+ **AI track**
65
+
66
+ - What files/commands were **not** run but should have been?
67
+ - What is **assumed** vs read from the repo?
68
+ - Where could the model **confabulate** (paths, APIs, CI status)?
69
+ - What test or verifier would **fail** if run now?
70
+
71
+ **Operator track**
72
+
73
+ - What business outcome is this supposed to achieve?
74
+ - What gates were **skipped or compressed** and why?
75
+ - What would make you **reject** this if you were a reviewer today?
76
+ - What are you **not** doing because of this work?
77
+
78
+ ### 3. Question bank
79
+
80
+ Pick the highest-leverage questions from each category (Flash: at least one per category; Full: all that apply).
81
+
82
+ | Category | Example challenges |
83
+ | --- | --- |
84
+ | **Evidence** | What single experiment would prove this wrong? Who can reproduce it? |
85
+ | **Scope** | What is explicitly **out** of scope? What adjacent bug is still open? |
86
+ | **Gates** | Which SDLC gate is weakest right now? Was human review bypassed? |
87
+ | **Reversibility** | Rollback plan? Feature flag? Migration backward-compatible? |
88
+ | **Incentives** | Why ship **now**? What pressure is causing false confidence? |
89
+ | **Dual control** | Did the same agent both implement and declare success? |
90
+ | **Secrets & safety** | Any `.env`, PII, or irreversible shell risk accepted without approval? |
91
+
92
+ ### 4. Verdict
93
+
94
+ Issue one verdict for the **combined** AI+operator posture:
95
+
96
+ | Verdict | Meaning |
97
+ | --- | --- |
98
+ | **BLOCKED** | Missing criteria, unknown evidence, or gate violation — do not ship |
99
+ | **NEEDS EVIDENCE** | Direction OK but proof missing — name exact commands/artifacts |
100
+ | **PROCEED WITH RISKS** | Known gaps documented; operator accepts residual risk in writing |
101
+
102
+ ### 5. Next actions
103
+
104
+ List **concrete** next steps (who: AI vs operator), e.g.:
105
+
106
+ - Run `npm test` / named test and paste outcome.
107
+ - Run `harness-verifier` or `sdlc-auditor`.
108
+ - Operator writes 3 acceptance criteria.
109
+ - Re-grill after evidence lands.
110
+
111
+ ## Output template
112
+
113
+ ```markdown
114
+ ## Grill Me — <topic>
115
+
116
+ ### Claim ledger
117
+ - AI: ...
118
+ - Operator: ...
119
+ - Acceptance criteria: ...
120
+
121
+ ### AI challenges
122
+ 1. ...
123
+
124
+ ### Operator challenges
125
+ 1. ...
126
+
127
+ ### Verdict: BLOCKED | NEEDS EVIDENCE | PROCEED WITH RISKS
128
+
129
+ ### Required before proceed
130
+ - [ ] ...
131
+
132
+ ### Residual risks (if proceeding)
133
+ - ...
134
+ ```
135
+
136
+ ## Integration with this repo
137
+
138
+ - **Honesty** — Separate facts, estimates, assumptions, and opinions in the claim ledger.
139
+ - **`sdlc-regulatory`** — Map findings to the gate that failed or was skipped.
140
+ - **`harness-engineering`** — Treat completion claims as proposals until independently verified.
141
+ - **`nvidia-skillspector-check`** — When the session is about **landing a new skill**, grill whether Skillspector artifacts exist before merge.
142
+
143
+ ## Anti-patterns
144
+
145
+ - Asking leading questions that let the operator vent without falsifiable tests.
146
+ - Grilling only the AI while ignoring the operator's gate-skipping.
147
+ - Ending with "looks good" without a verdict and explicit next actions.
148
+ - Replacing auditors or SDLC — grill is **pre-flight pressure**, not sign-off.
package/opencode.json CHANGED
@@ -6,7 +6,8 @@
6
6
  "instructions": [
7
7
  "AGENTS.md",
8
8
  "instructions/rules/sdlc-gates.md",
9
- "instructions/rules/harness-engineering.md"
9
+ "instructions/rules/harness-engineering.md",
10
+ "instructions/rules/nvidia-skillspector-check.md"
10
11
  ],
11
12
  "skills": {
12
13
  "paths": [
package/package.json CHANGED
@@ -1,10 +1,11 @@
1
1
  {
2
2
  "name": "@daochild/agents-config",
3
- "version": "2.1.0",
3
+ "version": "2.2.0",
4
4
  "description": "Shared, version-controlled configuration for AI coding agents: layout, skills, subagents, commands, rules, and an always-on AI-driven SDLC governance framework.",
5
5
  "keywords": [
6
6
  "ai-agents",
7
7
  "agent-configuration",
8
+ "skills",
8
9
  "agent-skills",
9
10
  "coding-assistant",
10
11
  "developer-tools",
@@ -16,7 +17,9 @@
16
17
  "compliance",
17
18
  "workflow",
18
19
  "opencode",
19
- "claude-code"
20
+ "claude-code",
21
+ "harness",
22
+ "skillspector"
20
23
  ],
21
24
  "homepage": "https://github.com/daochild/agents-config#readme",
22
25
  "bugs": {