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/anton-abyzov/specweave/frameworkgit clone --depth 1 https://github.com/anton-abyzov/specweaveWhat 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 | $0.00036 | $0.04424 |
| Opus 5 | $0.00018 | $0.02212 |
| Sonnet 5 | $0.00007 | $0.00885 |
| Haiku 4.5 | $0.00004 | $0.00442 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 531 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecWeave Framework Expert
Project Overrides
Skill Memories: If .specweave/skill-memories/framework.md exists, read and apply its learnings.
I am an expert on the SpecWeave framework - a spec-driven development framework for Claude Code (and other AI coding assistants). I have deep knowledge of its structure, rules, conventions, and best practices.
Core Philosophy
SpecWeave follows spec-driven development with increment-based workflows:
- Specification First - Write WHAT and WHY before HOW
- Incremental Delivery - Ship small, complete features
- Living Documentation - Docs update automatically via hooks
- Source of Truth Discipline - Single source, zero duplication
- Multi-Tool Support - Works with Claude, Cursor, Copilot, and generic AI
Increment-Based Development
What is an Increment?
An increment = a complete feature with:
spec.md- Product requirements (WHAT and WHY) — requiredplan.md- Technical architecture (HOW to implement) — optional, for complex features onlytasks.md- Task breakdown (WORK to do) — requiredmetadata.json- State tracking — required
When to skip plan.md: Bug fixes, simple migrations, hotfixes, and straightforward tasks where spec.md already describes the approach.
spec.md Mandatory Fields
CRITICAL: spec.md YAML frontmatter MUST include project (and board for 2-level structures):
# 1-level structure (single-project or multiProject):
---
increment: 0001-feature-name
project: my-project # REQUIRED
---
# 2-level structure (ADO area paths, JIRA boards, umbrella teams):
---
increment: 0001-feature-name
project: acme-corp # REQUIRED
board: digital-operations # REQUIRED for 2-level
---
Why? Ensures increment syncs to correct location in living docs. Without explicit project/board, sync-specs may fail or place specs in wrong folder.
Detection: Use src/utils/structure-level-detector.ts to determine if 1-level or 2-level structure is needed.
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 · 531 lines · 36 tokens per session scan A 9ea7df77557e
framework is a command published in the GitHub repository anton-abyzov/specweave (159 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 4,424 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 2026-08-30.
Other commands, from other repositories
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).
plan-regression-tests
Plan regression tests for existing code with it.skip statements.
export
Export the wiki (or architecture model) to markdown, HTML, JSON, or Structurizr DSL.
doc
Use this command to create a new feature doc, how-to, concept, reference, or troubleshooting guide — it scaffolds the file, frontmatter, structure, and sidebar entry.
review-teardown
Delete a review branch to free the shared Pantheon review slot.
dev-docs-update
Update dev documentation before context compaction.