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 skills/ghostwright/phantom/mirrornpx skills add ghostwright/phantom --skill mirrorgit clone --depth 1 https://github.com/ghostwright/phantomWhat 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 | $0.00022 | $0.00947 |
| Opus 5 | $0.00011 | $0.00474 |
| Sonnet 5 | $0.00004 | $0.00189 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
mirror scanned grade A with 1 finding 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 yesterday.
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.
Strips warnings and disclaimerslowAnti-refusal
Omitting safety caveats hides risk from the user and is a common jailbreak preamble.
The goal is honest, warm observation. Never moralize. Never prescribe. Offer what you saw and let the user decide what it means. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mirror: the weekly self-audit
Goal
Play back the last seven days to the user from memory. Not a task report. Not a highlight reel. A reflection that surfaces what the user could not see themselves: patterns, postponements, commitments made and broken, hours worked outside stated bounds, topics that consumed disproportionate mental energy, interpersonal frictions that recurred, decisions made without clear rationale.
The goal is honest, warm observation. Never moralize. Never prescribe. Offer what you saw and let the user decide what it means.
Steps
1. Pull the last seven days from memory
Call mcp__phantom-reflective__phantom_memory_search with days_back: 7, memory_type: "all", and a broad query like "this week" or the user's name. Return at least 20 episodes and 10 facts if available.
Success criteria: you have a list of episodes and facts from the last seven days. If the memory system is degraded and returns empty, tell the user honestly and stop.
2. Anchor with sessions
Call mcp__phantom-reflective__phantom_list_sessions with days_back: 7, limit: 50. Note which channels were active, how many turns each conversation ran, and where cost clustered.
Success criteria: you can reference specific sessions by channel and day when you describe a pattern.
3. Look for patterns across the week
Read the episodes and facts for:
- Repeated themes the user kept returning to.
- Commitments the user made ("I will", "I'll get back", "by Friday", "let me send") and whether subsequent memory shows follow-through.
- Postponements: things the user pushed off multiple days in a row.
- Unusual working hours: sessions outside the user's stated working bounds.
- Topics that ate disproportionate mental energy: multiple long sessions on one theme.
- Decisions made without stated rationale.
- Interpersonal friction that recurred with the same person or in the same channel.
Success criteria: you have identified between three and five patterns that you can cite to specific memory episodes.
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.
- yesterday First seen · 68 lines · 22 tokens per session scan A 92e6c910cc88
mirror is a skill published in the GitHub repository ghostwright/phantom (1,463 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 947 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (strips warnings and disclaimers). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
good-first-issue-batch
File a batch of contributor-ready GitHub issues from the seeds backlog, re-verifying every candidate against HEAD first so no dead issue reaches a contributor. Activate for prompts like "file some good first issues", "open a batch of GFIs", "publish backlog issues to GitHub", "find contributor-ready work", or after an…
seeds-issue-audit
Audit and triage open Seeds (sd) issues — find which can be closed, auto-close high-confidence completed ones, and report borderline cases. Activate for prompts like "audit open issues", "which seeds issues can be closed", "clean up the issue tracker", "triage the seeds backlog".
os-eco-dep-sync
Bump warren onto the latest published @os-eco/ versions across package.json + bun.lock and the Dockerfile CLI pins, then run the gates and open a PR. Use when checking if warren is on the newest burrow/plot/canopy/seeds/mulch/sapling.
release
Prepare, cut, and verify a warren release — tracker audits, version bump, CHANGELOG curation, ROADMAP update, push, then watch the pipeline through to published artifacts.
warren-dogfood-pipeline
Full prioritize → dispatch → shepherd → track pipeline against the live warren instance. Audits the seeds backlog around a focus theme, dispatches the surviving issues to warren agents one at a time, babysits the resulting PRs to merge (update-branch, conflict-repair runs, auto-merge), and closes the loop in the…
writing-skills
Use when a task reveals a recurring, multi-step capability worth saving for future sessions — writing a new Norma skill, or improving an existing self-authored one, via skillwrite.