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 agentmods add skills/parcadei/continuous-claude-v3/groupsnpx skills add parcadei/Continuous-Claude-v3 --skill groupsgit 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/groups)<a href="https://agentmods.dev/skills/parcadei/continuous-claude-v3/groups"><img src="https://agentmods.dev/badge/skills/parcadei/continuous-claude-v3/groups.svg" alt="Measured on agentmods" 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 | $0.00010 | $0.00982 |
| Opus 5 | $0.00005 | $0.00491 |
| Sonnet 5 | $0.00002 | $0.00196 |
| Haiku 4.5 | $0.00001 | $0.00098 |
Grade A, and why
groups 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 2d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Groups
When to Use
Use this skill when working on groups problems in abstract algebra.
Decision Tree
-
*Is G a group under operation ?
- Check closure: a,b in G implies a*b in G?
- Check associativity: (ab)c = a(bc)?
- Check identity: exists e such that ea = ae = a?
- Check inverses: for all a exists a^(-1) such that a*a^(-1) = e?
- Verify with
z3_solve.py prove "group_axioms"
-
Subgroup Test
- Show H is non-empty (usually by showing e in H)
- Show that for all a, b in H: ab^(-1) in H
z3_solve.py prove "subgroup_criterion"
-
Homomorphism Proof
- Verify phi(ab) = phi(a)phi(b) for all a, b in G1
- Note: phi(e1) = e2 and phi(a^(-1)) = phi(a)^(-1) follow automatically
sympy_compute.py simplify "phi(a*b) - phi(a)*phi(b)"
-
Order and Structure
- Element order: smallest n where a^n = e
- Group order: |G| = number of elements
- Lagrange: |H| divides |G| for subgroup H
Tool Commands
Z3_Group_Axioms
uv run python -m runtime.harness scripts/z3_solve.py prove "ForAll([a,b,c], op(op(a,b),c) == op(a,op(b,c)))"
Z3_Subgroup
uv run python -m runtime.harness scripts/z3_solve.py prove "subgroup_criterion"
Sympy_Simplify
uv run python -m runtime.harness scripts/sympy_compute.py simplify "phi(a*b) - phi(a)*phi(b)"
Key Techniques
From indexed textbooks:
- [Abstract Algebra] Write a computer program to add and multiply mod n, for any n given as input. The output of these operations should be the least residues of the sums and products of two integers. Also include the feature that if (a,n) = 1, an integer c between 1 and n — 1 such that a-c = | may be printed on request.
- [Abstract Algebra] With a certain amount of elementary argument (calculations in A7, for example see Exercise 27) it can be shown that there is, up to isomorphism, a unique simple group of order 168 (it is not always the case that there is at most one simple group of a given order: there are 2 nonisomorphic simple groups of order +8! We could further show that such a G would have no elements of order pg, p and q distinct primes, no elements of order 9, and that distinct Sylow subgroups would intersect in the identity. We could then count the elements in Sylow p-subgroups for all primes p and we would find that these would total to exactly |G|.
- [Abstract Algebra] Some Techniques Before listing some techniques for producing normal subgroups in groups of a given (“medium”) order we note that in all the problems where one deals with groups of order n, for some specific n, it is first necessary to factor n into prime powers and then to compute the permissible values of np, for all primes p dividing n. We emphasize the need to be comfortable computing mod p when carrying out the last step. The techniques we describe may be listed as follows: (1) Counting elements.
- [Abstract Algebra] Composition Series and the Hélder Program Sec. This proof takes 255 pages of hard mathematics. Part (2) of the Hélder Program, sometimes called the extension problem, was rather vaguely formulated.
- [Abstract Algebra] APPLICATIONS IN GROUPS OF MEDIUM ORDER The purpose of this section is to work through a number of examples which illustrate many of the techniques we have developed. These examples use Sylow’s Theorems ex- tensively and demonstrate how they are applied in the study of finite groups. Motivated by the Holder Program we address primarily the problem of showing that for certain n every group of order n has a proper, nontrivial normal subgroup (i.
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.
- 2d ago First seen · 69 lines · 10 tokens per session scan A 02941c02ede5
groups is a skill published in the GitHub repository parcadei/Continuous-Claude-v3 (3,936 stars, last pushed 7mo ago), licensed MIT. It adds 10 tokens to every session and 982 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
course
Process an online course into detailed vault notes — one per lecture, with slides and transcripts synthesized. Use this skill whenever the user shares a course URL, syllabus page, or lecture playlist and wants structured notes from it. Also triggers on "process this course", "take notes on these lectures", "course…
process
CORE learning workflow — use this whenever the user has a source note open (paper, post, book, lecture, course, clipping) and wants to extract knowledge, understand what they just read, or build it into their vault. Triggers on "process this note", "process this paper", "extract concepts", "what can I learn from…
recall
Spaced repetition and retrieval practice engine for the vault. Use when the user wants a review session, recall practice, to test what they remember, or to resurface notes. Triggers on "review session", "what should I review", "recall practice", "resurface notes", "spaced repetition", "quiz me", "what do I know…
book-analyzer
Analyze a book (EPUB/PDF) and generate detailed chapter-by-chapter notes with extracted key concepts. Use when given a book file path to process.
fizzy-workflow
Use for guided Fizzy.do workflows: "set up Fizzy", "configure Fizzy for this project", "sync my work to Fizzy", "review my Fizzy progress", "end of session cleanup". Provides step-by-step guidance for common operations.
self-learning
Autonomously research any technology, library, framework, or API. Discovers official documentation, extracts key information from authoritative sources, verifies across multiple pages, and generates a reusable Claude skill (SKILL.md) with installation, examples, and best practices.