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
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.
npx skills add parcadei/Continuous-Claude-v3 --skill tldr-deepgit clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3Wrote 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/skills/parcadei/continuous-claude-v3/tldr-deep)<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/tldr-deep"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/tldr-deep/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/skills/parcadei/continuous-claude-v3/tldr-deep"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/tldr-deep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00023 | $0.00782 |
| Opus 5 | $0.00012 | $0.00391 |
| Sonnet 5 | $0.00005 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
tldr-deep 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TLDR Deep Analysis
Full 5-layer analysis of a specific function. Use when debugging or deeply understanding code.
Trigger
/tldr-deep <function_name>- "analyze function X in detail"
- "I need to deeply understand how Y works"
- Debugging complex functions
Layers
| Layer | Purpose | Command |
|---|---|---|
| L1: AST | Structure | tldr extract <file> |
| L2: Call Graph | Navigation | tldr context <func> --depth 2 |
| L3: CFG | Complexity | tldr cfg <file> <func> |
| L4: DFG | Data flow | tldr dfg <file> <func> |
| L5: Slice | Dependencies | tldr slice <file> <func> <line> |
Execution
Given a function name, run all layers:
# First find the file
tldr search "def <function_name>" .
# Then run each layer
tldr extract <found_file> # L1: Full file structure
tldr context <function_name> --project . --depth 2 # L2: Call graph
tldr cfg <found_file> <function_name> # L3: Control flow
tldr dfg <found_file> <function_name> # L4: Data flow
tldr slice <found_file> <function_name> <target_line> # L5: Slice
Output Format
## Deep Analysis: {function_name}
### L1: Structure (AST)
File: {file_path}
Signature: {signature}
Docstring: {docstring}
### L2: Call Graph
Calls: {list of functions this calls}
Called by: {list of functions that call this}
### L3: Control Flow (CFG)
Blocks: {N}
Cyclomatic Complexity: {M}
[Hot if M > 10]
Branches:
- if: line X
- for: line Y
- ...
### L4: Data Flow (DFG)
Variables defined:
- {var1} @ line X
- {var2} @ line Y
Variables used:
- {var1} @ lines [A, B, C]
- {var2} @ lines [D, E]
### L5: Program Slice (affecting line {target})
Lines in slice: {N}
Key dependencies:
- line X → line Y (data)
- line A → line B (control)
---
Total: ~{tokens} tokens (95% savings vs raw file)
When to Use
- Debugging - Need to understand all paths through a function
- Refactoring - Need to know what depends on what
- Code review - Analyzing complex functions
- Performance - Finding hot spots (high cyclomatic complexity)
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.
- 9d ago First seen · 108 lines · 23 tokens per session scan A 906d221db52d
tldr-deep is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,938 stars, last pushed 7mo ago), licensed MIT. It adds 23 tokens to every session and 782 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.
Other skills, from other repositories
md-audit
Read-only code quality audit — scan the current working directory for common issues (bugs, dead code, security hotspots, missing error handling) and return a prioritised findings report. No files are edited. Use when asked to "audit the code", "quick audit", "find issues", "code scan", or "what's wrong with this…
cocoreview
CocoReview — structured code review with six-severity findings vocabulary, progressive disclosure architecture, and universal anti-pattern baseline. Invoked via $review [file] [--complexity] [--security] [--architecture] [--language ].
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
adjudicate-review
Turn an incoming set of findings — from an AI reviewer, a referee report, a code review, a linter, or a second model — into verified fixes, without letting a confident misread damage correct work. Every finding is a CANDIDATE until checked against the actual source. Use whenever you receive review comments, audit…
performance
Diagnose React runtime performance with React Doctor traces, live render outlines, Long Animation Frames, interaction timing, and component render evidence. Use when invoked as /performance for a slow interaction, unexpected re-renders, or a measured before-and-after comparison.