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 agents/evolution-foundation/evo-nexus/mirror-retrogit clone --depth 1 https://github.com/evolution-foundation/evo-nexusWrote 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/agents/evolution-foundation/evo-nexus/mirror-retro)<a href="https://agentmods.dev/agents/evolution-foundation/evo-nexus/mirror-retro"><img src="https://agentmods.dev/badge/agents/evolution-foundation/evo-nexus/mirror-retro.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 | $0.00273 | $0.01919 |
| Opus 5 | $0.00137 | $0.00959 |
| Sonnet 5 | $0.00055 | $0.00384 |
| Haiku 4.5 | $0.00027 | $0.00192 |
Grade A, and why
mirror-retro 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 4d 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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.
- 4d ago First seen · 154 lines · 273 tokens per session scan A be937463147a
mirror-retro is an agent published in the GitHub repository evolution-foundation/evo-nexus (530 stars, last pushed 3mo ago), with no licence file. It adds 273 tokens to every session and 1,919 once invoked, about $0.0014 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 agents, from other repositories
git-learner
Mines durable engineering memories from git commit diffs and stores them in LTM. Use to onboard a repo, backfill history after enabling gitLearn, or harvest patterns after a sprint. Reads diffs in its own context so raw git output never reaches the main thread.
okf-librarian
Bibliothécaire du bundle de connaissance OKF (okf/). À utiliser dès qu'une session a besoin de contexte projet (architecture, vision, marketing, roadmap, conventions) AVANT d'agir. Il lit le bundle dans SON propre contexte et ne renvoie qu'une synthèse courte + citations — ce qui garde le contexte principal léger et…
agentweaver
Drives the Agentweaver multi-agent orchestration platform end-to-end via its MCP tools. Use to create/manage projects, assemble teams from blueprints/scenarios, submit and supervise runs through the Coordinator, manage backlog/workflows/blueprints, review and pull run artifacts, and curate project memory and…
memory-promoter
Analyzes session transcripts and sprint summaries to identify high-value patterns for promotion to long-term BaseCoat memory contributions. USE FOR: extract reusable patterns from transcripts, identify conventions worth promoting, review sprint summaries for learnings. DO NOT USE FOR: writing code/instructions…
learnings-curator
PM subagent that promotes recurring pattern: tags from resolved bug, feature, or observation entries into Learning entries (L###) under /learnings/. Idempotent. Delegates deterministic curation to hooks/scripts/board-curate-learnings.sh; this agent dispatches the script and returns curation schema 0.3.0 verbatim.
memory-curator
Session and workspace management specialist. MUST BE USED for creating sessions, organizing workspaces, and managing memory lifecycle. Use PROACTIVELY when user mentions projects, sessions, or organization.