signal-intake

signal-intake is a skill for Claude Code from ryanzhao1011/workframe. It costs 116 tokens per session (2,319 once invoked), scanned A, original, MIT.

A procedure for recording incoming signals as issues or memory entries, with rules for checking existing records, merging duplicates, and handling replacements.

In plain words
What is it for?
It is for writing field reports, issues, and memory updates into the project’s established files and formats.
Why use it?
It reduces duplicate or conflicting records and makes sure important changes are confirmed or logged according to their priority.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the core plugin — 38 skills, 4 agents, 11 hooks shipped together

Good fit It is for writing field reports, issues, and memory updates into the project’s established files and formats.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ryanzhao1011/workframe/signal-intake
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 ryanzhao1011/workframe --skill signal-intake
Clone the repo
git clone --depth 1 https://github.com/ryanzhao1011/workframe

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 38 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 signal-intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/ryanzhao1011/workframe/signal-intake/github.svg)](https://agentmods.dev/skills/ryanzhao1011/workframe/signal-intake)
Your own site
<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/signal-intake"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/signal-intake/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.

agentmods 80×15 button for signal-intake

Your own site · 80×15
<a href="https://agentmods.dev/skills/ryanzhao1011/workframe/signal-intake"><img src="https://agentmods.dev/badge/skills/ryanzhao1011/workframe/signal-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,319 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 $0.00116 $0.02319
Opus 5.5 $0.00046 $0.00928
Sonnet 5.5 $0.00023 $0.00464
Haiku 4.5 $0.00012 $0.00232

Measured 14d ago against content hash 1e2576e03ffd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

signal-intake 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 14d 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.

plugins/core/skills/signal-intake/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

信号入账工序

必载片已经判完「触发没有、算哪一档、落哪个点」。本文只管落盘那一步的形状。

1. 写入前必做(A.U.N. 工序)

Assert 存在 → Update 合并 → New 新增,三选一,顺序不可换。

  1. 落笔前先 Read 目标文件,确认它存在且结构匹配。不存在就参照同目录已有文件的格式创建;YAML 字段名与现有条目不一致时以现有条目为准。绝不猜测字段结构。
  2. 检索同主题旧条目——同一事实 / 口径 / 对象,表述可能完全不同,按语义判,不是按字符串找。
  3. 三选一:
    • 无同主题 → 新增
    • 有同主题 → 改写合并成一条:保留信息量更大的表述,条目内标注更新时间与来源;被取代的旧表述移对应 notes.md 留档,不并排堆同主题的多条版本
    • 已有等价记录 → 不写,在响应里说明「该口径已有记录」

同主题合并、异主题追加:不同主题才追加新条目。查重合并的判据与 librarian 的融合整理 SOP 同源,别另立一套。

2. 执行规范

  1. P0 先确认再写入:任何 P0 变更一律「回显摘要 → 等用户确认 → 写入」。顺序不许颠倒,不允许先写后确认。
  2. P1/P2 即时更新:通过排除判据后立即写,不等额外确认。但目标若在受保护资产清单内,或是需求文档 / 批量看板任务,仍走草稿与 owner 角色路径。
  3. 冲突处理:新信息与现有数据冲突时先提示用户确认,不自动覆盖;确认后走 supersede——保留最新、旧的移 notes 或归档区留档,不直接删。
  4. 位序自检:写记忆或事件之前先自检「这个事实是不是已经被更早的那一步消费过了」。已写入则跳过,只处理未消费的那部分。
  5. 升级条件:P1/P2 满足升级条件时按升级后的档处理。
  6. 关联任务:P0 类紧急变更在用户确认后,往看板 tasks: 末尾追加单条 status: pending(tags: [auto-update, <类别>]),仅作信号标记入队,不自动派发。

3. Issue 落盘

类别 文件 备注
安全 / 权限 / Prompt 泄露 projects/issues/SEC-{序号}.yaml 泄露类 title 前缀 [Prompt泄露]
故障 projects/issues/BUG-{序号}.yaml

模板随项目骨架初始化,见项目内 projects/issues/TEMPLATES.md——字段以那份为准,本文不复制字段表(复制一份就是第二个事实源)。序号取该前缀下当前最大值 +1,建之前先列目录,别按记忆猜。

4. 记忆条目的写入格式

纠正类条目的形状是硬要求——librarian 的同主题查重与 entry_key 归一都吃这个形状:

- [纠正] {日期}:{正确信息}(用户纠正,原错误认知:{错误认知})

日期在标记之后、正确信息之前;括注在末尾。位置与措辞都不是自由发挥的:查重按语义找同主题,而归一按前缀截断,形状漂了两边都会 miss。

指针化的那一档(业务事实类,正文已移交权威文档)写成:

- [纠正] {日期}:{一行结论}(权威口径见 [[<文档路径>]])

指针化不算清理:标记、日期与 sidecar 保护都还在。

5. sidecar 与 entry_key

写入 MEMORY.md 之后同步维护 <state>/memory-index.json。文件不存在先初始化:

{"__schema__":"workframe.memory-index.v2","entries":{}}

entry_key 三段式:

<scope>:<YYYY-MM-DD>:<正确信息前 20 字规范化>

规范化三条,缺一不可,顺序不可颠倒:

  1. 先删除全部空白字符
  2. 再取前 20 字(Unicode 字符数,不是字节)
  3. 同日同前 20 字碰撞时追加 -2 / -3

顺序反了会算出另一个 key:先截断会让落在前 20 字内的空白占掉有效字符,两种顺序对同一条目得出不同 key,跨 producer 的 supersede 与去重随之 miss。改序之前生成的历史 key 保持不变,不回改。

Read the full file on GitHub · 130 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. 14d ago First seen · 130 lines · 116 tokens per session scan A 1e2576e03ffd

Subscribe to this mod's changes

signal-intake is a skill published in the GitHub repository ryanzhao1011/workframe (5 stars, last pushed 16d ago), licensed MIT. It adds 116 tokens to every session and 2,319 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-01.

Related

Other skills, from other repositories

md-hive-sync

Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…

chaitanyagiri/munder-difflin · 109 tokens

pod-resume

Reconstruct context for a returning developer. Reads .cocoplus/ state and generates a narrative summary of project status, last achievements, pending tasks, recent decisions, available patterns, CocoCupper insights, and recommended next action.

Snowflake-Labs/cocoplus · 50 tokens

link-ticket-to-session

Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…

JayantDevkar/claude-code-karma · 91 tokens

write-prd

Write PRD — Product Requirements Documents with structured 8-section templates, user stories, acceptance criteria, and value proposition validation. Use when writing PRDs, defining product requirements, creating user stories with INVEST criteria, or building go/no-go decision frameworks.

yonatangross/orchestkit · 54 tokens

td-task-management

Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions. Includes workflows for single-issue focus, multi-issue work sessions, and structured handoffs. Essential for AI-assisted development where context windows reset…

marcus/td · 65 tokens

handoff

Write a short handoff note for the next chat or a teammate, with what is done, what is open, what comes next and what was rejected and why. Saves it to project memory so the next chat sees it at the start, and prints it so it can be pasted into a message or a pull request. Use when the user ends a piece of work…

Avijit07x/claude-db · 87 tokens