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 richardcb/oh-my-gemini --skill persistencegit clone --depth 1 https://github.com/richardcb/oh-my-geminiWrote 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/richardcb/oh-my-gemini/persistence)<a href="https://agentmods.dev/skills/richardcb/oh-my-gemini/persistence"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/persistence/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/richardcb/oh-my-gemini/persistence"><img src="https://agentmods.dev/badge/skills/richardcb/oh-my-gemini/persistence.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 | $0.00052 | $0.01507 |
| Opus 5.5 | $0.00021 | $0.00603 |
| Sonnet 5.5 | $0.00010 | $0.00301 |
| Haiku 4.5 | $0.00005 | $0.00151 |
Grade A, and why
persistence scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:3000/health 2>/dev/null || echo "Server not running" How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persistence Skill
Goal
Enable Claude/Gemini to work persistently on a task until it's truly complete, with automatic verification, retry logic, and alternative approaches when blocked.
Activation Triggers
This skill should be activated when:
- User includes "ralph", "persistent", or "don't give up" in their request
- A task has failed and needs retry with a different approach
- Complex multi-step work requires sustained focus
Core Behavior
Never Give Up Philosophy
When this skill is active, you must:
- Set a clear, measurable goal from the user's request
- Work iteratively toward that goal
- Verify progress after each significant action
- Try alternatives when an approach fails
- Only stop when: goal achieved, user interrupts, or truly impossible
Retry Protocol
On failure:
- Analyze the failure - What specifically went wrong?
- Identify alternatives - What other approaches exist?
- Try the next approach - Don't repeat the same mistake
- Track attempts - After 5 consecutive failures on the same sub-problem, escalate
Verification Protocol
After each significant action, verify:
For code changes:
# Check syntax/compilation
npm run typecheck 2>&1 | tail -20 || tsc --noEmit 2>&1 | tail -20
# Check tests
npm test 2>&1 | tail -30
# Check lint
npm run lint 2>&1 | tail -20
For file creation:
# Verify file exists and has content
ls -la [filepath] && wc -l [filepath]
# Check file can be parsed (for JSON, etc.)
cat [filepath] | head -20
For features:
# If there's a dev server, check it's running
curl -s http://localhost:3000/health 2>/dev/null || echo "Server not running"
# Check for runtime errors in logs
tail -20 *.log 2>/dev/null || echo "No logs"
State Tracking
Maintain mental state during persistence:
## Persistence State
### Goal
[Clear statement of what success looks like]
### Progress
- [x] Step 1: [Description] ✓
- [x] Step 2: [Description] ✓
- [ ] Step 3: [Current step]
- [ ] Step 4: [Remaining]
### Attempts on Current Step
1. [Approach 1] - Failed: [reason]
2. [Approach 2] - In progress...
### Blockers
- [Any identified blockers]
### Alternative Approaches Available
1. [Alternative 1]
2. [Alternative 2]
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.
- 1mo ago First seen · 250 lines · 52 tokens per session scan A 4f06f176aecf
persistence is a skill published in the GitHub repository richardcb/oh-my-gemini (18 stars, last pushed 7mo ago), licensed MIT. It adds 52 tokens to every session and 1,507 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
prompt-engineering
Use this skill when asked to create, refine, analyze, or optimize prompts for Large Language Models (LLMs). This skill ensures adherence to prompt engineering best practices and enforces a rigorous design workflow.
meteocontrol-assistant
Specialized assistant for monitoring and analyzing solar installations via the MeteoControl VCOM API. Use it to troubleshoot production drops, triage alerts, and generate system reports.
troubleshooter
Specialized in system-wide troubleshooting using metrics and logs.
logs-expert
Expert in writing and optimizing LogsQL queries for VictoriaLogs.
metrics-expert
Expert in MetricsQL and system monitoring with VictoriaMetrics.
configure-ecc
Interactive installer for Everything Gemini CLI — guides users through selecting and installing skills and rules to user-level or project-level directories, verifies paths, and optionally optimizes installed files.