self-iteration

self-iteration is a skill for Claude Code, Codex from ryanzhao1011/workframe. It costs 23 tokens per session (4,596 once invoked), scanned B, original, MIT.

A self-improvement workflow that studies the agent's past activity and recorded results to suggest changes.

In plain words
What is it for?
It reviews usage metrics, event logs, notes, issues, and previously applied proposals, then checks whether those proposals worked.
Why use it?
It helps identify repeated problems or unused processes instead of relying on memory or guesswork.

Skill for Claude CodeCodex

Part of the core plugin — 37 skills, 4 agents, 11 hooks shipped together

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/ryanzhao1011/workframe/self-iteration
Any agent
npx skills add ryanzhao1011/workframe --skill self-iteration
Clone the repo
git clone --depth 1 https://github.com/ryanzhao1011/workframe

Made for: Claude Code, Codex.

Or install core, the plugin that ships this one along with the rest of its 37 skills, 4 agents, 11 hooks.

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 self-iteration

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryanzhao1011/workframe/self-iteration.svg)](https://agentmods.dev/skills/ryanzhao1011/workframe/self-iteration)
Your own site
<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/self-iteration"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/self-iteration.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,596 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00023 $0.04596
Opus 5 $0.00012 $0.02298
Sonnet 5 $0.00005 $0.00919
Haiku 4.5 $0.00002 $0.00460

Measured 4d ago against content hash db66a70e96db, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

self-iteration scanned grade B 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 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

python "$(cat .claude/workframe-state/plugin-root.txt)/scripts/maintenance_workorder.py" \
plugins/core/skills/self-iteration/SKILL.md · 236 lines

How it starts

The opening of the file, as written. The whole thing — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.

自迭代技能

5 阶段流程

阶段 1:数据收集 + 已应用提案闭环验证

(a) 数据源收集(主要在 .claude/workframe-state/(另含 .claude/agent-memory/projects/ 下若干路径,见下表) 下,由 hook / deterministic scripts / system skills 维护):

  • .claude/workframe-state/skill-metrics.yaml — 技能/规则使用汇总(由 recompute_skill_metrics.py 从 events.jsonl 重算)
  • .claude/workframe-state/events.jsonl — 原始事件流(审计/追因时读,日常决策读 metrics 即可)
  • .claude/workframe-state/activity-state.json — 活跃度 + dormant 状态 + pending_maintenance(status=open);若 dormant=truewake_up_pending=true 则本次自迭代直接退出(除非由 /core:maintenance-review 显式触发)。pending_maintenance 里的 kind/details 是本次识别模式的重要线索,应与 notes/events 证据一起纳入阶段 2 分析。
  • .claude/agent-memory/*/notes.md — 各角色微反思
  • .claude/agent-memory/shared/MEMORY.mdshared/notes.md — 跨角色共识
  • projects/changelog.md — 历史操作日志
  • projects/issues/ — 历史问题记录(若有结构化文件)

(b) 扫描 projects/proposals/applied/*.yamlverified: null 的条目做闭合验证

  • 对每条读取 verify_by(日期)和 verify_signal(需观察到的信号表达式)
  • 若今天 ≥ verify_by
    • 读取 skill-metrics.yaml / events.jsonl,判断 verify_signal 是否已达成
    • signal_met=true → append events.jsonl:{"ts":"<ISO-8601>","type":"proposal_verified","proposal_id":"<id>","signal_met":true};将提案文件中 verified: true
    • signal_met=false → append events.jsonl:{"ts":"<ISO-8601>","type":"proposal_verified","proposal_id":"<id>","signal_met":false},再 append {"ts":"<ISO-8601>","type":"proposal_failed","proposal_id":"<id>"}(供 audit / 下一轮 self-iteration 反思用;proposal_failed 不计入 check-iteration-trigger.py 的 problem 加权分recompute_skill_metrics.py 实际统计的是 proposal_verified.signal_met=false 累加到 proposal_failures_count,不直接读 proposal_failed);将提案文件中 verified: false

阶段 2:模式识别 + 置信度评分

从阶段 1 收集的数据中识别候选模式:

  • 重复问题:notes / changelog / events 中有明确证据显示同类问题重复出现。occurrences 是置信度计算的证据输入,不是硬门槛;低于 3 次仍可计算 confidence,但通常低于提案阈值。
  • 低效流程:仅当 notes / changelog / issues 中存在明确的耗时或阻塞记录时方可使用;系统无耗时事件,不得凭感觉声称"平均耗时高于预期"
  • 未覆盖场景:仅当 notes / changelog 中有明确的"用户重复手工处理"记录时方可使用;不得无证据臆造"手工处理"场景
  • 技能低成功率:近 30 天某 skill success/invocations < 0.6(来自 skill-metrics.yaml)。仅供人工判读,不作自动触发信号success 为 agent 自评,实测从未产出 false,作触发条件永不满足)——用它时须结合 notes / user_correction 等独立证据,不得仅凭该比值提案。
  • 提案失败回路:有 proposal_failed 事件的旧提案 → 反思当初假设,识别失败原因。

Read the full file on GitHub · 236 lines

Files

What ships with it

3 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.

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 · 236 lines · 23 tokens per session scan B db66a70e96db

Subscribe to this mod's changes

self-iteration is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 17d ago), licensed MIT. It adds 23 tokens to every session and 4,596 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

discover

Runtime catalog — list all installed skills, agents, and active hooks. Use when you want to know what's available.

martineserios/thebrana · 25 tokens

html-prototype

Generate HTML prototypes (single-file, browser-openable) for product mockups using the user's design system — fonts, color scales, radii, shadows, components, all driven by a tokens.css file. Use when the user asks to make a 原型 / mockup / HTML 设计图 / 设计图给前端 for a PRD module, OR redesign an existing prototype. Output…

mayuemarsha-del/pm-skills · 97 tokens

feature-acceptance

研发提测后接管浏览器,对照 PRD(必给)+ HTML 原型(自动找)逐项验收线上实现,产出差异清单(实现 / 部分实现 / 未实现 / 与原型或 PRD 不一致)+ 截图证据 + 阻塞问题排序。Use whenever PM 说「验收 XX」「跑一下 XX」「研发提测了」「对一下需求和线上」「点一下 XX 看符不符合需求」「看哪些实现了哪些没做」「上线前 check」「灰度验收」「acceptance」「QA check」,or 给出 PRD 路径 + 线上 URL 让 Claude 走流程。也适用于 PM 想自己点某功能、判断和需求差异时陪她一起跑。区别于 prd skill:本 skill 验证线上现状,不修改 PRD…

mayuemarsha-del/pm-skills · 192 tokens

prd

Write, rewrite, polish, restructure, or review product requirements documents (PRDs). Use whenever a task touches a 需求文档 / PRD —— 新写、重构、统一口径、补页面结构 / 字段 / 规则 / 边界 / 异常处理、加指标口径定义、按数据看板或某类骨架组织章节,或把讨论 / 会议记录整理成正式产品文档。Trigger even when the user does NOT say "写需求" —— e.g. "把这个加到…

mayuemarsha-del/pm-skills · 202 tokens

gbg

Convert any plan, PRD, feature idea, or brief into a sequenced goal-by-goal execution document with reviewer-gated commits — for everyday feature development, MVPs, migrations, refactors, and hardening alike. Generates a project brief, per-goal scope/tasks/acceptance criteria, an LLM-reviewer prompt (Codex/etc.), a…

cielebak/goal-by-goal · 150 tokens

ui-walkthrough

把一份 UI 设计 HTML 和研发上线的页面,同视口、同状态截图比对 + 读 computed style 实锤,产出 UI 还原度差异清单(结构 / 组件 / 颜色 / 字体 / 圆角 / 图标 / 间距 七维,每条标明设计值 vs 线上值)。Use whenever PM 说「UI 走查」「走查一下 UI」「对一下 UI」「UI 还原度」「还原度走查」「线上跟设计稿对一下」「前端还原得对不对」「页面跟这份 HTML 对一下」「UI 验收」「设计还原走查」,或给出 设计 HTML 路径 + 线上 URL 让 Claude 比视觉差异。区别于 feature-acceptance skill:那个验业务逻辑 / 字段 / 操作…

mayuemarsha-del/pm-skills · 231 tokens