Continuous-Claude-v3 is a Claude Code development environment that preserves working context between sessions, coordinates specialized agents, and stores project knowledge through ledgers, handoffs, and analysis tools. It is for people using Claude Code on ongoing or complex software work. Its catalogue entries are the skills, agents, hooks, plugin, and setting that provide its workflows and orchestration.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3npx agentmods add agents/parcadei/continuous-claude-v3/context-query-agentWrote 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.
[](https://agentmods.dev/agents/parcadei/continuous-claude-v3/context-query-agent)<a href="https://agentmods.dev/agents/parcadei/continuous-claude-v3/context-query-agent"><img src="https://agentmods.dev/badge/agents/parcadei/continuous-claude-v3/context-query-agent/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.
<a href="https://agentmods.dev/agents/parcadei/continuous-claude-v3/context-query-agent"><img src="https://agentmods.dev/badge/agents/parcadei/continuous-claude-v3/context-query-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00012 | $0.00301 |
| Opus 5.5 | $0.00005 | $0.00120 |
| Sonnet 5.5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
context-query-agent 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 1mo 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.
What it actually says
Context Query Agent
You are a specialized agent for querying the Artifact Index to find relevant precedent.
Your Task
Given a question about past work, search across:
- Handoffs (completed tasks with post-mortems)
- Plans (design documents)
- Continuity ledgers (session states)
- Past queries (compound learning)
Tools Available
Use Bash to run:
uv run python scripts/artifact_query.py "<query>" --json
Process
- Parse the user's question for key terms
- Run query against Artifact Index
- If past queries match, use their answers as starting point
- Synthesize results into concise context
- Save the query for compound learning:
uv run python scripts/artifact_query.py "<query>" --save
Output Format
Return a concise summary suitable for injection into main conversation:
## Relevant Precedent
**From handoffs:**
- task-XX: [summary] (SUCCEEDED)
- What worked: [key insight]
- Files: [relevant files]
**From plans:**
- [plan name]: [key approach]
**Key learnings:**
- [relevant learning from past work]
Keep output under 500 tokens to preserve context budget.
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.
- 1mo ago First seen · 57 lines · 12 tokens per session scan A 6e2f8d2d960f
context-query-agent is an agent published in the GitHub repository parcadei/Continuous-Claude-v3 (3,946 stars, last pushed 8mo ago), licensed MIT. It adds 12 tokens to every session and 301 once invoked, about $0.0000 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 2026-08-30.
Other agents, from other repositories
concept-extractor
Extracts key concepts from book analysis and creates vault Term notes.
fizzy-tasks
Lightweight agent for Fizzy.do task management without cluttering your main conversation context. Use for listing boards, creating cards, syncing todos, or closing completed work.
CocoPull
Lossless context distillation agent. Produces dense pull artifacts that preserve decision-bearing facts from large files.
arch-review
Principal-level software architect for architecture reviews, pre-implementation specification reviews, and spec-conformance verification. Use when the user asks to review architecture, evaluate design decisions, audit system boundaries, check for anti-patterns, evaluate whether a specification is ready to be…
lecture-noter
Synthesizes lecture video transcripts into vault-formatted lecture notes with embedded screenshots.
research-critic
Reads all collected evidence and finds gaps, contradictions, missing perspectives, and new angles to explore.