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 commands/extremeclarity/claude-plugins/add-frameworkgit clone --depth 1 https://github.com/extremeclarity/claude-pluginsWhat 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 | $0.00008 | $0.00442 |
| Opus 5 | $0.00004 | $0.00221 |
| Sonnet 5 | $0.00002 | $0.00088 |
| Haiku 4.5 | $0.00001 | $0.00044 |
Grade A, and why
add-framework 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.
What it actually says
Add Framework
Create a reusable thinking framework from the current conversation.
The Bar
Only add frameworks that will clearly help in future sessions.
Before creating a framework, ask:
-
Reuse Test: Will this framework be applied to similar problems in the future? If it's a one-off analysis, don't create a framework.
-
Future Value Test: Can you articulate a concrete future scenario where having this framework changes Claude's approach for the better?
-
Structure Test: Does it have clear structure (criteria, steps, matrix, model)? Vague advice doesn't make a framework.
Process
-
Review — Look at the recent conversation for patterns, decision criteria, or mental models that emerged.
-
Check for duplicates — Read
.worldview/frameworks/index.txt. If a similar framework exists, ask the user: update existing or create new? -
Align terminology — Read
.worldview/terminology.txt. Use consistent terms from the existing terminology. -
Write the framework — Create
.worldview/frameworks/[framework-name].mdwith:- Clear title
- When to use this framework
- The framework structure (criteria, steps, decision matrix, etc.)
- Examples if helpful
Use kebab-case for framework name (e.g.,
decision-matrix.md,error-handling-patterns.md). -
Update index — Append to
.worldview/frameworks/index.txt:[framework-name].md: One-line summary -
Extract terms — If the framework introduces terms with non-obvious meanings, append to
.worldview/terminology.txt:[YYYY-MM-DD] *Term*: DefinitionApply the same bar: only add terms that will help Claude in future sessions.
Guidelines
- Keep frameworks focused on a single problem type
- Use the user's language and framing where possible
- Reference existing terminology to maintain consistency
- Keep framework files concise — capture the structure, not exhaustive explanation
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 · 56 lines · 8 tokens per session scan A 9fc81e65c831
add-framework is a command published in the GitHub repository extremeclarity/claude-plugins (4 stars, last pushed 6mo ago), licensed MIT. It adds 8 tokens to every session and 442 once invoked, about $0.0000 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.