01c-copy-diff

01c-copy-diff is an agent for coding agents from assafkip/kipi-system. It costs 20 tokens per session (629 once invoked), scanned A, original, MIT.

A comparison agent that checks yesterday’s drafted outreach messages against the messages the founder actually sent or posted.

In plain words
What is it for?
It compares generated copy with LinkedIn activity and records the differences, including the original and final text when a message was edited.
Why use it?
It shows whether drafts were used, edited, skipped, or could not be verified, so repeated changes can improve future drafts.

Agent

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 agents/assafkip/kipi-system/01c-copy-diff
Clone the repo
git clone --depth 1 https://github.com/assafkip/kipi-system

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 01c-copy-diff

README.md
[![agentmods](https://agentmods.dev/badge/agents/assafkip/kipi-system/01c-copy-diff.svg)](https://agentmods.dev/agents/assafkip/kipi-system/01c-copy-diff)
Your own site
<a href="https://agentmods.dev/agents/assafkip/kipi-system/01c-copy-diff"><img src="https://agentmods.dev/badge/agents/assafkip/kipi-system/01c-copy-diff.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 629 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 $0.00020 $0.00629
Opus 5 $0.00010 $0.00315
Sonnet 5 $0.00004 $0.00126
Haiku 4.5 $0.00002 $0.00063

Measured yesterday against content hash e756febe3bd2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

01c-copy-diff 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 yesterday.

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.

q-system/.q-system/agent-pipeline/agents/01c-copy-diff.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent: Copy Diff (Learnings Loop)

Compare yesterday's generated copy against what the founder actually posted. Log edits.

Reads

  • {{BUS_DIR}}/../{yesterday}/hitlist.json (generated copy)
  • Chrome MCP: founder's actual LinkedIn activity

Writes

  • {{BUS_DIR}}/copy-diffs.json

Instructions

Step 1: Find yesterday's hitlist

Calculate yesterday's date. Read {{QROOT}}/.q-system/agent-pipeline/bus/{yesterday}/hitlist.json. If missing, write {"date":"{{DATE}}","diffs":[],"note":"no previous hitlist found"} and exit.

Step 2: Check what was posted

Use Chrome MCP to check https://www.linkedin.com/in/me/recent-activity/all/ and messaging. For each hitlist action: check if comment/DM/CR was sent, compare generated vs actual text.

Step 3: Classify

  • used_as_is: >95% match
  • edited: 50-95% match (capture the diff AND the full original + posted text)
  • skipped: not posted/sent
  • unknown: couldn't verify

Step 4: Write

For edited status, include original_text (yesterday's drafted copy) and posted_text (what the founder actually posted). The full-text pair feeds route-overrides-to-learn.py, which builds inbox files for the learn-from-correction skill. edit_summary stays as a short human-readable note.

{"date":"{{DATE}}","yesterday":"YYYY-MM-DD","actions_checked":10,"diffs":[{"action_rank":1,"contact_name":"...","action_type":"comment|dm|connection_request","status":"edited","edit_summary":"shortened, removed CTA","original_text":"<full drafted text>","posted_text":"<full posted text>"}],"stats":{"used_as_is":0,"edited":0,"skipped":0,"unknown":0},"persisted_to_sqlite":false}

For non-edited statuses, omit original_text and posted_text (they only carry information when an override exists).

Step 5: Persist edits to SQLite

For each edited action, insert into copy_edits table in {{QROOT}}/.q-system/data/metrics.db. Required columns: date, contact_name, action_type, original (full drafted text), edited (full posted text), edit_summary. The full-text pair is what route-overrides-to-learn.py reads from to build learn-from-correction inputs.

Read the full file on GitHub · 49 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. yesterday First seen · 49 lines · 20 tokens per session scan A e756febe3bd2

Subscribe to this mod's changes

01c-copy-diff is an agent published in the GitHub repository assafkip/kipi-system (109 stars, last pushed today), licensed MIT. It adds 20 tokens to every session and 629 once invoked, about $0.0001 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 2026-09-03.