persistence

persistence is a skill for Claude Code from rtazima/claude-proj-blueprint. It costs 59 tokens per session (1,024 once invoked), scanned A, original, MIT.

A repeated implementation mode that keeps working through a project checklist until its tests and build requirements pass, or the iteration limit is reached.

In plain words
What is it for?
It is for implementing a project from a requirements document, running its tests and build commands, and tracking which acceptance criteria pass.
Why use it?
It reduces the need to supervise each attempt when a change requires several rounds of coding and checking.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

Good fit It is for implementing a project from a requirements document, running its tests and build commands, and tracking which acceptance criteria pass.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rtazima/claude-proj-blueprint/persistence
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.

Any agent
npx skills add rtazima/claude-proj-blueprint --skill persistence
Clone the repo
git clone --depth 1 https://github.com/rtazima/claude-proj-blueprint

Made for: Claude Code.

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 persistence

README.md
[![agentmods](https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/persistence.svg)](https://agentmods.dev/skills/rtazima/claude-proj-blueprint/persistence)
Your own site
<a href="https://agentmods.dev/skills/rtazima/claude-proj-blueprint/persistence"><img src="https://agentmods.dev/badge/skills/rtazima/claude-proj-blueprint/persistence.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,024 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00059 $0.01024
Opus 5 $0.00030 $0.00512
Sonnet 5 $0.00012 $0.00205
Haiku 4.5 $0.00006 $0.00102

Measured 7d ago against content hash fba2726af485, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

persistence 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 7d 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.

.claude/skills/persistence/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persistence Mode (Ralph)

Iterative implementation loop that does NOT stop until all acceptance criteria from the PRD pass — or max iterations are reached. Named after Sisyphus: the boulder never stops.

Rules

  1. Never ask for confirmation between iterations — just keep going
  2. Never claim "done" without evidence — run the actual test/build commands
  3. Track iteration count — stop at max iterations even if not all criteria pass
  4. Report status after each iteration — which criteria pass, which fail, what you'll try next
  5. Each iteration must make progress — if the same criterion fails 3 times with the same approach, try a different strategy
  6. Preserve working code — never break passing criteria to fix a failing one

Configuration

  • Max iterations: [SPEC] (default: 5)
  • Test command: [SPEC] (from CLAUDE.md Commands section)
  • Build command: [SPEC] (from CLAUDE.md Commands section)

Workflow

Phase 1: Extract criteria

  1. Read the PRD at the given path
  2. Extract ALL acceptance criteria into a numbered checklist
  3. Print the checklist: [ ] Criterion 1, [ ] Criterion 2, etc.
  4. Identify the test/build command from CLAUDE.md or project config

Phase 2: Implement (loop)

For each iteration (1 to max_iterations):

── Iteration {N}/{max} ──────────────────────
  1. Assess: which criteria are NOT yet passing?
  2. Plan: what specific changes will address the next failing criterion?
  3. Implement: make the changes
  4. Verify: run tests/build to check ALL criteria (not just the one you worked on)
  5. Report:
    ✅ Criterion 1: passing
    ✅ Criterion 2: passing
    ❌ Criterion 3: failing — [reason]
    ── {passed}/{total} criteria passing ──
    
  6. If ALL criteria pass → go to Phase 3
  7. If not all pass → continue to next iteration

Phase 3: Finalize

  1. Run full test suite one final time
  2. Run slop-cleaner skill on changed files (if available)
  3. Print final status:
    ── Ralph Complete ──────────────────────
    Iterations: {N}/{max}
    Criteria: {passed}/{total} passing
    Files changed: [list]
    ────────────────────────────────────────
    
  4. If max iterations reached with failures, clearly state which criteria still fail

Read the full file on GitHub · 99 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. 7d ago First seen · 99 lines · 59 tokens per session scan A fba2726af485

Subscribe to this mod's changes

persistence is a skill published in the GitHub repository rtazima/claude-proj-blueprint (20 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,024 once invoked, about $0.0003 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 2026-08-30.