ic1558/literal_executor
skills/literal_executor/SKILL.md
--- name: literal_executor version: 1.0 domain: governance owner: gmx mandatory_read: YES execution_modes: [apply, prove] memory_requirement: none --- # Literal Executor **"The spec is law. Engineering judgment is suspended."** ## Role Activate when executing against a frozen blueprint, CLC prompt, or any spec marked as BINDING LAW. Overrides Gemini's default abstraction-and-optimize behavior. ## Trigger Conditions Activate this skill when any of the following appear in the task: - "bluepr
development
Updated Apr 19, 2026
$ install --global
skillsauthnpx skillsauth add ic1558/0luka literal_executorInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 19, 2026, 5:08 AM4.5s1 file scanned
SKILL.md
- name:
- literal_executor
- version:
- 1.0
- domain:
- governance
- owner:
- gmx
- mandatory_read:
- YES
- execution_modes:
- [apply, prove]
- memory_requirement:
- none
Literal Executor
"The spec is law. Engineering judgment is suspended."
Role
Activate when executing against a frozen blueprint, CLC prompt, or any spec marked as BINDING LAW. Overrides Gemini's default abstraction-and-optimize behavior.
Trigger Conditions
Activate this skill when any of the following appear in the task:
- "blueprint", "execution prompt", "CLC prompt"
- "exact string", "exact order", "exact values"
- "do not paraphrase", "literal compliance"
- "law not guidance", "frozen design"
Procedure (in order, no skipping)
- Read the full spec before writing a single line of code
- Extract all EXACT strings, field names, function locations, and paths — list them explicitly
- For each implementation step: quote the spec line that authorizes it
- If a spec line is ambiguous → STOP. Report the ambiguity. Do not resolve it yourself.
- After implementation: diff your output against spec line-by-line
- Flag any deviation, even cosmetic (message text, whitespace in strings, variable placement)
Guardrails
- Do NOT optimize logic placement — implement where the spec says, not where it "makes sense"
- Do NOT paraphrase strings — copy character-for-character
- Do NOT add fields the spec does not list
- Do NOT remove fields the spec requires
- Do NOT use synonyms for enum values
- Engineering judgment RE-ENABLES only after all spec requirements are satisfied and verified
Output Contract
Every output must include:
{
"execution_mode": "apply",
"skill": "literal_executor",
"spec_lines_followed": ["<quote each spec line implemented>"],
"deviations": [],
"governed": true
}
If deviations is non-empty → verdict is NON_COMPLIANT. Do not self-patch without reporting first.
Fail Modes
| Failure | Required Response | |---------|------------------| | Spec line is ambiguous | STOP — surface exact ambiguity to operator | | Two spec lines contradict | STOP — do not pick one — surface both | | You paraphrased a required string | Flag as deviation in output | | You moved logic to a "better" place | Flag as deviation in output | | You added a field not in spec | Flag as deviation in output |
Escalation
If more than 2 deviations are found in self-audit → do NOT self-patch. Surface the full list to CLC for adjudication before continuing.
Related Skills
ic1558/skills/auto-workflow-creator
development
VerifiedTrustedCommunity
--- name: auto-workflow-creator description: Create a new skill from a workflow you just performed. Generates a valid 3-layer Anthropic-style skill — YAML frontmatter (name + description + triggers), imperative instruction body, and optional scripts/ subdirectory — and prints the registration commands per target runtime (Claude Code auto-discovers from ~/.claude/skills/; Codex needs an explicit [[skills.config]] entry in ~/.codex/config.toml; OpenCode needs a registry entry in ~/.opencode/openco
SKILL.mdUpdated May 27, 2026
ic1558/skills/cost-control
tools
VerifiedTrustedCommunity
# Cost-Control Skill Enforce token discipline and model routing optimization (Flash vs Pro) via the Gemini CLI 0.40 Gemma local router for governed-agent workflows. ## Guidelines - **Preference for Local/RTK/File Tools:** Always prioritize local tools (ls, read_file, grep_search) and RTK for initial data gathering before calling model logic. - **Flash-First Routing:** - Route all routine code analysis, file reads, summarization, search, and classification tasks to `gemini-3.5-flash-preview` o
SKILL.mdUpdated May 1, 2026
ic1558/skills/verify-first
development
VerifiedTrustedCommunity
--- name: verify-first description: Run verification gates before and after code changes, prioritize health and regressions, and fail closed on missing evidence. Mandatory Read: YES --- # Verify First Mandatory Read: YES ## Workflow 1. Capture baseline verify results. 2. Apply minimal changes. 3. Re-run targeted and system-level verify commands. 4. Report explicit pass/fail evidence. ## Caps - Run deterministic verification commands. - Compare before/after outcomes. - Block claims without pr
SKILL.mdUpdated Apr 19, 2026
ic1558/vera
testing
VerifiedTrustedCommunity
Use this skill when you need to perform a READ-ONLY forensic validation of a completed task (evidence), verify compliance against a TaskSpec, or issue a formal verdict (PASS/FAIL) before GMX approval. Strictly forbids modification or execution.
SKILL.mdUpdated Apr 19, 2026