Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/kok-o/koko-contextos-agentsnpx agentmods add skills/kok-o/koko-contextos-agents/gemini-precisionWrote 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/kok-o/koko-contextos-agents/gemini-precision)<a href="https://agentmods.dev/skills/kok-o/koko-contextos-agents/gemini-precision"><img src="https://agentmods.dev/badge/skills/kok-o/koko-contextos-agents/gemini-precision/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kok-o/koko-contextos-agents/gemini-precision"><img src="https://agentmods.dev/badge/skills/kok-o/koko-contextos-agents/gemini-precision.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00045 | $0.01192 |
| Opus 5 | $0.00023 | $0.00596 |
| Sonnet 5 | $0.00009 | $0.00238 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
gemini-precision 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gemini-precision
Overview
High-precision operational standard designed specifically to harness the high speed and expansive context window of Google Gemini models while eliminating common LLM failure modes: hasty assumptions, partial code placeholders (// ...), unverified assertions, and scope creep.
When to Use
Activate whenever:
- Executing non-trivial code modifications, refactoring, bug fixes, or architecture design.
- The user requires maximum rigor, reliability, and precision from Gemini.
- Handling complex multi-file changes where accidental side-effects must be zero.
Rules & Patterns
1. The Read-Before-Write Invariant (Zero Assumptions)
Never write code based on assumptions about the codebase.
- Before modifying a function or creating an integration, always inspect the actual files using
view_fileorgrep_search. - Check the exact runtime, framework version, and installed dependencies (e.g. React 19 vs 18, Next.js 15 vs 14, Tailwind v4 vs v3, Zod vs Joi) in
package.jsonor config files before generating code. - Verify imported symbol names and parameter signatures directly from source files.
2. The Zero-Placeholder Invariant (Complete Code Only)
Never produce lazy, incomplete, or stubbed output.
- ❌ Forbidden:
// TODO: implement logic here// ... rest of existing code ...// ... existing imports ...- Mock stub returns when real integration is required
- ✅ Mandatory:
- Provide 100% complete, fully-implemented, compilable, and drop-in ready code.
- When replacing a block of code, include all necessary imports, type definitions, and edge-case handling.
3. The Proof-of-Work Invariant (Verification Before Completion)
Never claim a task is complete without tool-verified evidence.
- When modifying code or configuration:
- Run the project validator or compiler (
node .agents/ctx.js validate,tsc --noEmit, etc.). - Run unit and integration tests (
npm test,pytest, etc.). - Run linter and formatting checks (
npm run lint:md,eslint, etc.).
- Run the project validator or compiler (
- If a test or validation fails, do not guess: read the exact error trace, fix the root cause, and re-run until green.
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 · 143 lines · 45 tokens per session scan A 9ef9512fd413
gemini-precision is a skill published in the GitHub repository kok-o/koko-contextos-agents (2 stars, last pushed 7d ago), licensed MIT. It adds 45 tokens to every session and 1,192 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
dev-fix
Unified developer workflow for fixing bugs. Analyzes issue-tracker context, cross-checks docs/code, proposes a solution, implements the fix, verifies locally, and delivers a PR/MR.
incident-hotfix
Mitigate a production incident or urgent regression first, then route to root-cause remediation and a postmortem.
common-performance-engineering
Enforce universal standards for high-performance development. Use when profiling bottlenecks, reducing latency, fixing memory leaks, improving throughput, or optimizing algorithm complexity in any language.
common-debugging
Troubleshoot systematically using the Scientific Method. Use when debugging crashes, tracing errors, diagnosing unexpected behavior, or investigating exceptions.
flutter-error-handling
Implement functional repository error recovery with Either/Failure patterns in Flutter. Use when handling exceptions or dartz Either types in data flows; defer UI-only retry buttons.
quality-engineering-test-healing
Failure taxonomy and allowed/forbidden repairs for a failing E2E test. Use when a Playwright/Maestro/Detox/XCUITest/Espresso/Appium test fails and you must decide whether to repair the test or route to a real bug.