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.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 | $0.00052 | $0.01507 |
| Opus 5 | $0.00026 | $0.00754 |
| Sonnet 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 8d 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.
- 8d 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 (16 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 1,507 once invoked, about $0.0003 per session on Opus 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
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.
autonomous-agent-harness
Transform Gemini CLI into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Gemini CLI's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous…
dmux-workflows
Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Gemini CLI, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.
connections-optimizer
Reorganize the user's X and LinkedIn network with review-first pruning, add/follow recommendations, and channel-specific warm outreach drafted in the user's real voice. Use when the user wants to clean up following lists, grow toward current priorities, or rebalance a social graph around higher-signal relationships.
email-ops
Evidence-first mailbox triage, drafting, send verification, and sent-mail-safe follow-up workflow for ECC. Use when the user wants to organize email, draft or send through the real mail surface, or prove what landed in Sent.
google-workspace-ops
Operate across Google Drive, Docs, Sheets, and Slides as one workflow surface for plans, trackers, decks, and shared documents. Use when the user needs to find, summarize, edit, migrate, or clean up Google Workspace assets without dropping to raw tool calls.