Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add MatrixFounder/Agentic-development --skill skill-self-improvement-verificatorgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/matrixfounder/agentic-development/skill-self-improvement-verificator)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/skill-self-improvement-verificator"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/skill-self-improvement-verificator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00024 | $0.00828 |
| Opus 5 | $0.00012 | $0.00414 |
| Sonnet 5 | $0.00005 | $0.00166 |
| Haiku 4.5 | $0.00002 | $0.00083 |
Grade A, and why
skill-self-improvement-verificator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Self-Improvement Verificator
[!IMPORTANT] TIER 3 (Meta-Skill): Use ONLY when creating or modifying
System/Agents,System/Docs, orGEMINI.md.
1. Purpose
This skill acts as a Guardian for the Framework itself. Before any changes are applied to the "Brain" of the IDE (Prompts, Skills, Docs), this skill verifies that the proposed changes are safe, consistent, and do not break the "Constitutional" rules (Tier 0 skills).
2. Modes
This skill operates in two distinct modes depending on the current Stage.
Mode A: SPECIFICATION AUDIT (Analysis Phase)
Trigger: When docs/TASK.md proposes a Framework Upgrade.
Action: Verify the Specification.
Checklist:
- Root Integrity: Does the update respect
core-principles(Stub-First, Atomicity)? - Skill Compatibility: Do new Agents/Prompts explicitly load
TIER 0skills? - Documentation: Does the task include updating
System/Docs/to reflect changes? - Migration: Does the task describe how to migrate existing sessions (if applicable)?
Mode B: PLAN AUDIT (Planning Phase)
Trigger: When docs/PLAN.md details the implementation steps.
Action: Verify the Execution Plan.
Checklist:
- Verification Step: Is there an explicit step to run
pytestorvalidation_scripts? - Rollback: Is there a backup step (e.g.,
cp GEMINI.md GEMINI.bak)? - Atomic Updates: Are changes broken down into safe, verifiable chunks?
- Test Coverage: Does the plan include adding/updating tests for new framework features?
3. Usage (Workflow Integration)
This skill is primarily called by the /framework-upgrade workflow.
# Example Usage in Workflow
- Validator: `spec-validator` (Standard)
- **Meta-Validator**: `skill-self-improvement-verificator` (Framework Safety)
4. Failure Conditions (Blocking)
If ANY of the following are found, STOP and return a CRITICAL failure:
- Removing
core-principlesorskill-safe-commandsfrom any Agent. - Modifying
GEMINI.mdwithout a corresponding update toSystem/Docs. - Creating a new Workflow without defining its Trigger in
GEMINI.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 71 lines · 24 tokens per session scan A ca721fe1e7b4
skill-self-improvement-verificator is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 24 tokens to every session and 828 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
workflow
Perform any development work on the ambient-ui component. Full workflow instructions.
08-debug
Reproduce and fix a known bug, or find an unknown root cause by hypothesis validation. Use when the user wants to fix a bug, find why something breaks, or reopen a stuck investigation. Not for building a feature or reviewing a diff.
hatch3r-bug-fix
Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
chimera-write-the-check-before-the-code
A criterion written after the implementation describes the implementation. Write the failing check first, watch it fail, then build.
Learn what defines effective BDD scenarios
Interactive guidance on writing complete, effective BDD scenarios for story-flow.
systematic-debugging
Structured root-cause debugging loop — reproduce, isolate, form a hypothesis, verify the fix. Use whenever a bug, crash, test failure, or unexpected behavior is reported.