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 Amatofrancesco99/thoughtweave --skill changesgit clone --depth 1 https://github.com/Amatofrancesco99/thoughtweaveWrote 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/amatofrancesco99/thoughtweave/changes)<a href="https://agentmods.dev/skills/amatofrancesco99/thoughtweave/changes"><img src="https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/changes/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/amatofrancesco99/thoughtweave/changes"><img src="https://agentmods.dev/badge/skills/amatofrancesco99/thoughtweave/changes.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 | $0.00051 | $0.02207 |
| Opus 5.5 | $0.00020 | $0.00883 |
| Sonnet 5.5 | $0.00010 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00221 |
Grade A, and why
changes 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.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/changes
Generate a human-readable explanation of implemented changes. The purpose is communication, not documentation. The audience includes developers, reviewers, managers, and stakeholders.
The skill is a tool for the developer, not a replacement. The developer stays at the centre - every decision about what to document, which trade-offs to highlight, and which risks to accept is driven by the developer's judgement. The skill surfaces information, but the developer decides what matters.
Pre-condition Check
Before any questions, verify that a specification exists for this feature:
- Determine the target folder (ask if not known or inheritable from context).
- Check if
spec.mdexists in that folder. - If
spec.mddoes not exist, refuse to proceed: "A changes document documents what changed relative to a specification. Without a spec, there is no anchor to compare against. Please run /sdd first to create a specification for this feature." - If
spec.mdexists but is incomplete, warn and ask whether to proceed or complete the spec first. - If
spec.mdis complete but lacks documented hidden assumptions, flag this and ask the user to review.
[!IMPORTANT] This check is non-negotiable. The changes skill cannot produce meaningful output without a spec.
Implementation Validation
Before generating the changes document:
- Read the
spec.mdto extract requirements, acceptance criteria, decisions, and constraints. - Inspect the actual implementation (code changes, file modifications, architecture) and verify each maps back to a corresponding item in the spec.
- If requirements from the spec are not addressed, flag them as unimplemented and ask if intentionally dropped.
- If the implementation includes behaviour not covered by the spec, flag it as untracked and ask for justification.
- If
AGENTS.mdexists, validate that the implementation respects its constraints, best practices, and architectural directives. Flag deviations.
Vulnerability Scanning
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 · 199 lines · 51 tokens per session scan A 1818373a7459
changes is a skill published in the GitHub repository Amatofrancesco99/thoughtweave (5 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 2,207 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
bulletproof-building-and-review
Use when reviewing code adversarially or building production-bound features where rigour matters more than speed. Required for code reviews ending in a verdict (PASS/HOLD), when verifying that "tests pass" actually proves a feature works end-to-end, before closing findings as non-issues, before signing off your own…
reviewer-fix-mode
Defines strict review-then-fix authority for reviewers. Use when a reviewer is allowed to repair findings after review, when avoiding reviewer-as-stealth-builder drift, or when verifying that fixes stay limited to documented findings.
k-review
An independent review of frozen Git base and head versions, checking both the written specification and project standards.
skill-quality-review
Review a proposed or existing SKILL.md before publication for practical scope, precise triggers, evidence quality, counterexamples, safety, overlap, composability, and honest lifecycle status. Use when creating, revising, promoting, deprecating, or merging agent skills.
behavior-preserving-refactoring
Restructure code without changing its observable contract. Use when an AI coding agent extracts modules, renames interfaces, reduces duplication, changes control flow, or modernizes implementation while behavior should remain stable.
dead-code-and-comment-cleanup
Identify dead code, duplicated literals, drift-prone declarations, and comments that restate implementation without deleting anything until usage and intent are verified. Use when an AI coding agent is asked to clean up unused code or redundant comments.