persist

persist is a skill for Claude Code, Codex from kimgoetzke/coding-agent-configs. It costs 47 tokens per session (842 once invoked), scanned A, original, MIT.

A skill for saving research, analysis, or other important results to disk so they remain available after the agent's conversation memory is cleared.

In plain words
What is it for?
Persisting investigation results, summaries, compliance research, comparisons, and other work that does not yet involve changing the code.
Why use it?
It prevents useful findings from being lost when a task is long or the conversation reaches its context limit.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kimgoetzke/coding-agent-configs/persist
Any agent
npx skills add kimgoetzke/coding-agent-configs --skill persist
Clone the repo
git clone --depth 1 https://github.com/kimgoetzke/coding-agent-configs

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for persist

README.md
[![agentmods](https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/persist.svg)](https://agentmods.dev/skills/kimgoetzke/coding-agent-configs/persist)
Your own site
<a href="https://agentmods.dev/skills/kimgoetzke/coding-agent-configs/persist"><img src="https://agentmods.dev/badge/skills/kimgoetzke/coding-agent-configs/persist.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.00842
Opus 5 $0.00023 $0.00421
Sonnet 5 $0.00009 $0.00168
Haiku 4.5 $0.00005 $0.00084

Measured 4d ago against content hash bc26d1fc0416, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

persist 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 4d 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.

skills/persist/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Core idea

  • Context window = RAM (volatile, limited)
  • Anything important gets written to disk.

Workflow

Step 1: Determine task type

Before doing any work, determine whether the user's request is primarily about understanding or documenting existing code in the current repository.

  • If yes → invoke the research-codebase skill instead. Do not continue with this skill.
    • Examples: "how does the auth flow work?", "document the payment service", "explain the middleware chain", "what classes handle X?"
  • If no → continue with Step 2.
    • Examples: no argument or "analyse this RFC", "summarise the compliance requirements", "investigate options for a new library", "compare approaches for X"

Step 2: Resolve the argument

If an argument was provided:

  • Treat it as the topic/subject to persist — use it to derive {topic} and proceed to Step 3.

If no argument was provided:

  • Summarise the conversation since the last persistence event (i.e. since the last invocation of persist, planning, planning-mode, research-mode, or any other skill that writes to .ai/). If no such event exists, summarise the entire conversation.
  • The summary must be structured around learnings, insights, and decisions — not a chronological account of what was said. Extract the substance: what was established, what was ruled out, what trade-offs were identified, what conclusions were reached.
  • Derive {topic} from the subject matter of that conversation segment.
  • Use the summary as the content to persist.

Step 3: Determine output location

Check whether this skill is being invoked within the context of an existing plan (i.e. you are aware of/working on a plan with a folder under {repo root}/.ai/planning/).

Within an existing plan:

  • Store output in {repo root}/.ai/planning/{existing plan folder}/{yyyy-mm-dd} {topic}.md
  • Example: .ai/planning/2026-04-09 refactor-auth-flow/2026-04-10 auth-middleware-analysis.md

Standalone (no existing plan):

Read the full file on GitHub · 77 lines

Changes

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.

  1. 4d ago First seen · 77 lines · 47 tokens per session scan A bc26d1fc0416

Subscribe to this mod's changes

persist is a skill published in the GitHub repository kimgoetzke/coding-agent-configs (2 stars, last pushed 15d ago), licensed MIT. It adds 47 tokens to every session and 842 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 2026-08-31.

Related

Other skills, from other repositories

codebase-memory

Use the codebase knowledge graph for structural code queries. Triggers on: explore the codebase, understand the architecture, what functions exist, show me the structure, who calls this function, what does X call, trace the call chain, find callers of, show dependencies, impact analysis, dead code, unused functions…

narumiruna/pi-extensions · 98 tokens

accordion-context-folding

Read this skill if you see {# FOLDED} markers in your context (e.g. {#3f9a2c FOLDED}), or if earlier parts of your context look summarized. Accordion is a desktop tool that may compact older context blocks to keep you under a token budget. The unfold tool restores a folded block (open from your next turn); the recall…

a-Fig/Accordion · 102 tokens

accordion-context-recall

Read this skill when you need to read the full content of a folded context block RIGHT NOW as a tool result — without opening it in your standing context. Use recall(codes) when you only need a value once and do not want to permanently restore the block. Accordion may fold older parts of your context to keep token…

a-Fig/Accordion · 89 tokens

memory-compounding

Review and sharpen persistent memory so it compounds instead of accumulating. Use when pruning pi-hermes-memory entries, doing monthly memory hygiene, or when the same lesson has been recorded multiple times.

romiluz13/auto-pi · 41 tokens

session-handoff

Hand off work to another Pi session — write a handoff doc, save key decisions to memory, and notify the target session via intercom. Use when a session is getting long, when you need to continue work in a fresh context, or when transferring work between projects/sessions. Composes handoff.ts (doc writer) + memory…

romiluz13/auto-pi · 83 tokens

session-search

Search and verify Joel's Pi, Claude, Codex, Cursor, Grok, and OpenCode session history. Use when asked to recover prior context, find exact transcript evidence, inspect session receipts, continue old work, or verify capture health. Prefer flowing recall before raw transcript search when the question is about prior…

joelhooks/pi-tools · 70 tokens