Big-AGI is an open-source workspace for using multiple AI models through chat and other AI functions. It is intended for engineers, founders, researchers, and other users who want to work with AI personas, model comparisons, image generation, voice, documents, and code-related features. The catalogue entries provide commands, instructions, and a skill for working with Big-AGI.
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.
git clone --depth 1 https://github.com/enricoros/big-AGIWrote 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/commands/enricoros/big-agi/changelog)<a href="https://agentmods.dev/commands/enricoros/big-agi/changelog"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/changelog/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/commands/enricoros/big-agi/changelog"><img src="https://agentmods.dev/badge/commands/enricoros/big-agi/changelog.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 | $0.00011 | $0.00674 |
| Opus 5 | $0.00005 | $0.00337 |
| Sonnet 5 | $0.00002 | $0.00135 |
| Haiku 4.5 | $0.00001 | $0.00067 |
Grade A, and why
changelog 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.
What it actually says
Generate changelog bullets for a single entry in https://big-agi.com/changes
Step 1: Find the starting date
IMPORTANT: This repo rebases frequently, so commits are INTERLEAVED throughout history.
New commits can appear at line 10, 500, or 1800. Use AUTHOR DATE (%ad) to filter - it's preserved during rebases.
If $ARGUMENTS provided, use it as the cutoff date.
If NO argument:
- Fetch https://big-agi.com/changes to get the most recent changelog date
- Use that date as the cutoff
Step 2: Get commits by author date
Filter commits by author date to catch ALL new commits regardless of position in history:
# For commits after Jan 10, 2026 (adjust date pattern as needed)
git log --oneline --no-merges --format="%h %ad %s" --date=short | grep "2026-01-1[1-9]\|2026-01-2\|2026-02"
# Verify interleaving by checking line numbers
git log --oneline --no-merges --format="%h %ad %s" --date=short | grep -n "2026-01-1[1-9]"
The line numbers prove commits are scattered (e.g., lines 14, 638, 1156, 1803 = interleaved).
Step 3: Write bullets
Real examples from big-agi.com/changes:
- "Gemini 3 Flash support with 4-level thinking: high, medium, low, minimal"
- "Cloud Sync launched! - long awaited and top requested"
- "Deepseek V3.2 Speciale comes with almost Gemini 3 Pro performance but 20 times cheaper"
- "Anthropic Opus 4.5 with controls for effort (speed tradeoff), thinking budget, search"
- "Login with email, via magic link"
- "Mobile UX fixes for popups drag/interaction"
Rules:
- Order by importance - most significant changes first, minor fixes last
- Feature-first, no verb prefixes - "Gemini 3 support" not "Add Gemini 3 support"
- Model names lead when it's about LLMs
- Specific details - "4-level thinking: high, medium, low, minimal" not "multiple thinking levels"
- One-liners - short, no fluff
- Consolidate commits - 10 persona editor commits = 1 bullet
- No corporate speak - no "enhanced", "streamlined", "robust", "leverage"
Skip: WIP, internal refactors, KB docs, automation, review cleanups, trivial fixes, deps bumps, CI changes.
Output: Just bullets, ready to paste. 2-5 bullets but adapt depending on scope, especially in relation to the usual https://big-agi.com/changes entries.
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 · 56 lines · 11 tokens per session scan A 848ab826bf5b
changelog is a command published in the GitHub repository enricoros/big-AGI (7,118 stars, last pushed today), licensed MIT. It adds 11 tokens to every session and 674 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 2026-08-30.
Other commands, from other repositories
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
ship
Ship is the operational release-prep flow for a connected project repo.
release-plan
A release-planning command for a software change. It documents the release scope, rollback plan, gradual or full rollout, and monitoring before waiting for human approval.
release
Standalone SDK release command for the BUILD repo. Not a workspace phase — runs independently after any number of implement/redteam cycles. Handles PyPI publishing, documentation deployment, and CI management for the kailash Python SDK and its framework packages.
doc-changelog
Generation and maintenance of the project changelog.