signal-harvester

signal-harvester is an agent for Claude Code from iamcxa/kc-claude-plugins. It costs 42 tokens per session (1,233 once invoked), scanned A, original, MIT.

An agent that searches a private journal, episodic memory, and a MEMORY.md file for signs that a plugin needs improvement.

In plain words
What is it for?
It searches using supplied keywords, compares findings with a plugin's goals and measurable signals, and returns confidence-rated YAML.
Why use it?
It gathers scattered feedback and past observations in one pass, even when one of its data sources is unavailable.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths.

Part of the kc-nightwatch plugin — 3 skills, 4 agents shipped together

Good fit It searches using supplied keywords, compares findings with a plugin's goals and measurable signals, and returns confidence-rated YAML.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/iamcxa/kc-claude-plugins/signal-harvester
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.

Clone the repo
git clone --depth 1 https://github.com/iamcxa/kc-claude-plugins

Made for: Claude Code.

Or install kc-nightwatch, the plugin that ships this one along with the rest of its 3 skills, 4 agents.

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-harvester

README.md
[![agentmods](https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/signal-harvester/github.svg)](https://agentmods.dev/agents/iamcxa/kc-claude-plugins/signal-harvester)
Your own site
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/signal-harvester"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/signal-harvester/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-harvester

Your own site · 80×15
<a href="https://agentmods.dev/agents/iamcxa/kc-claude-plugins/signal-harvester"><img src="https://agentmods.dev/badge/agents/iamcxa/kc-claude-plugins/signal-harvester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,233 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 $0.00042 $0.01233
Opus 5 $0.00021 $0.00616
Sonnet 5 $0.00008 $0.00247
Haiku 4.5 $0.00004 $0.00123

Measured 9d ago against content hash 0efd24230668, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

signal-harvester 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 9d 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.

kc-nightwatch/agents/signal-harvester.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Signal Harvester

You search for plugin improvement signals across three data sources and return structured YAML output.

Input

You receive these fields from the orchestrator:

  • plugin: plugin name (e.g., kc-pr-flow)
  • plugin_path: absolute path to plugin directory
  • repo: repository name (for PR routing)
  • keywords: list of search terms from nightwatch-targets.yaml
  • north_star: the plugin's qualitative north star goal
  • proxy_signals: list of measurable proxy signal IDs and descriptions

Search Strategy (strict order)

Search ALL available sources. Do not skip sources even if early sources return many results. If an MCP tool is unavailable (tool call fails with "not connected" or similar), log a warning and continue with remaining sources — never abort.

Source 1: Private Journal (last 14 days)

Use mcp__private-journal__search_journal with keyword combinations from the input.

If tool unavailable: Log [WARN] private-journal MCP not available — skipping journal source and continue to Source 2. This is common for users without the private-journal plugin.

Search pattern:

  1. Run 2-3 queries combining different keywords (e.g., "PR review friction", "create-pr workaround")
  2. Read promising entries in full to assess relevance
  3. Look for: complaints, friction, workarounds, failures, manual operations, repeated patterns, bugs discovered in live use

Max: 5 signals from this source.

Source 2: Episodic Memory

Use mcp__plugin_episodic-memory_episodic-memory__search with plugin name + key terms.

If tool unavailable: Log [WARN] episodic-memory MCP not available — skipping episodic source and continue to Source 3.

Search pattern:

  1. Search plugin name directly (e.g., "kc-pr-flow")
  2. Search 1-2 additional queries for cross-session recurring patterns
  3. Filter out conversation context injections (high match score but no insight)

Max: 3 signals from this source.

Source 3: MEMORY.md

Locate the project's auto-memory file. Try these paths in order:

  1. ~/.claude/projects/*/memory/MEMORY.md (glob for the current project)
  2. {plugin_path}/../MEMORY.md (workspace root)

Read the full file on GitHub · 143 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. 9d ago First seen · 143 lines · 42 tokens per session scan A 0efd24230668

Subscribe to this mod's changes

signal-harvester is an agent published in the GitHub repository iamcxa/kc-claude-plugins (3 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 1,233 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 agents, from other repositories

context-finder

Read-only, memory- and index-aware codebase search. Use for any investigation — "where is X", "how does Y work", "what calls Z", "is W still used", "where is V configured", "does this event/pattern get emitted anywhere" — BEFORE reaching for grep. Consults the knowledge graph, code index, and prior session memory…

futuregerald/futuregerald-claude-plugin · 111 tokens

wiki-ingest

Use this agent when ingesting URLs, files, or pasted text into the vault during automated maintenance cycles. Typical triggers include dev-loop IDLE DISCOVERY ingestion, batch source processing, or converting raw captures to typed-knowledge pages. See "When to invoke" in the agent body for worked scenarios.

karlorz/llm-wiki · 64 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens