Strict Enforcement

What it does

When your agent uses it

• Running claudikins-kernel:verify
• Checking implementation quality
• Deciding pass/fail verdicts
• Enforcing cross-command gates — requires actual evidence of code working

Example prompts

• “/strict-enforcement”

Requirements

• Pre-approved tools (allowed-tools): Read, Grep, Glob, Bash, WebFetch, Skill, mcp__plugin_claudikins-tool-executor_tool-executor__search_tools, mcp__plugin_claudikins-tool-executor_tool-executor__get_tool_schema, mcp__plugin_claudikins-tool-executor_tool-executor__execute_code

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Automated Quality Checks
2. 2Output Verification (catastrophiser)
3. 3Code Simplification (Optional)
4. 4Klaus Escalation
5. 5Human Checkpoint

What it can do on your machine

Read from SKILL.md and the folder at commit 8b626a4. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Grep
  • Glob
  • Bash
  • WebFetch
  • Skill
  • mcp__plugin_claudikins-tool-executor_tool-executor__search_tools
  • mcp__plugin_claudikins-tool-executor_tool-executor__get_tool_schema
  • mcp__plugin_claudikins-tool-executor_tool-executor__execute_code

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • npm
  • cargo
  • jq

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use npm, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Strict Enforcement loads about 2.7k tokens when it runs, and up to ~23k if it reads all its reference files. Until then it costs about 56 tokens; SKILL.md has 779 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~56

When it runs · the whole SKILL.md, loaded when a task matches

~2.7k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~23k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Grep, Glob, Bash, WebFetch, Skill, mcp__plugin_claudikins-tool-executor_tool-executor__search_

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from povvo/claudikins-kernel at commit 8b626a4, republished under its MIT licence (© povvo). 779 words, ~2,725 tokens.

name

strict-enforcement

description

Use when running claudikins-kernel:verify, checking implementation quality, deciding pass/fail verdicts, or enforcing cross-command gates — requires actual evidence of code working, not just passing tests

allowed-tools

Read, Grep, Glob, Bash, WebFetch, Skill, mcp__plugin_claudikins-tool-executor_tool-executor__search_tools, mcp__plugin_claudikins-tool-executor_tool-executor__get_tool_schema, mcp__plugin_claudikins-tool-executor_tool-executor__execute_code

Test fails?
├── Re-run failed tests
├── Pass 2nd time?
│   └── Yes → STOP: [Accept flakiness] [Fix tests] [Abort]
└── Fail 2nd time?
    ├── Run isolated
    └── Still fail? → STOP: [Fix] [Skip] [Abort]

Is mcp__claudikins-klaus available? (E-16)
├── No →
│   Offer: [Manual review] [Ask Claude differently] (E-17)
│   Fallback: [Accept with uncertainty] [Max retries, abort] (E-18)
└── Yes →
    Spawn klaus via SubagentStop hook

Verification Report
-------------------
Tests:  ✓ 47/47 passed
Lint:   ✓ 0 issues
Types:  ✓ 0 errors
Build:  ✓ success

Evidence:
- Screenshot: .claude/evidence/login-flow.png
- API test: POST /api/auth → 200 OK
- CLI test: mycli --help → exit 0

[Ready to Ship] [Needs Work] [Accept with Caveats]

# Both conditions MUST be true
ALL_PASSED=$(jq -r '.all_checks_passed' "$STATE")
HUMAN_APPROVED=$(jq -r '.human_checkpoint.decision' "$STATE")

if [ "$ALL_PASSED" != "true" ]; then
  exit 2  # Blocks claudikins-kernel:ship
fi

if [ "$HUMAN_APPROVED" != "ready_to_ship" ]; then
  exit 2  # Blocks claudikins-kernel:ship
fi

find . \( -name '*.ts' -o -name '*.py' -o -name '*.rs' \) \
  | xargs sha256sum > .claude/verify-manifest.txt

if [ ! -f "$EXECUTE_STATE" ]; then
  echo "ERROR: claudikins-kernel:execute has not been run"
  exit 2
fi

{
  "session_id": "verify-2026-01-16-1100",
  "execute_session_id": "execute-2026-01-16-1030",
  "branch": "execute/task-1-auth-middleware",
  "phases": {
    "test_suite": { "status": "PASS", "count": 47 },
    "lint": { "status": "PASS", "issues": 0 },
    "type_check": { "status": "PASS", "errors": 0 },
    "output_verification": { "status": "PASS", "agent": "catastrophiser" },
    "code_simplification": { "status": "PASS", "agent": "cynic" }
  },
  "all_checks_passed": true,
  "human_checkpoint": {
    "decision": "ready_to_ship",
    "caveats": []
  },
  "unlock_ship": true,
  "verified_manifest": "sha256:...",
  "verified_commit_sha": "abc123..."
}

© povvo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (references) in skills/strict-enforcement of povvo/claudikins-kernel.

• SKILL.md
• references/advanced-verification.md
• references/agent-integration.md
• references/cynic-rollback.md
• references/lint-fix-validation.md
• references/red-flags.md
• references/test-timeout-handling.md
• references/type-check-confidence.md
• references/verification-checklist.md
• references/verification-method-fallback.md
• references/verify-state-compression.md

Open the folder on GitHubat commit 8b626a4