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 alaarab/phren --skill phren-consolidategit clone --depth 1 https://github.com/alaarab/phrenWrote 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/alaarab/phren/phren-consolidate)<a href="https://agentmods.dev/skills/alaarab/phren/phren-consolidate"><img src="https://agentmods.dev/badge/skills/alaarab/phren/phren-consolidate/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/alaarab/phren/phren-consolidate"><img src="https://agentmods.dev/badge/skills/alaarab/phren/phren-consolidate.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 | $0.00018 | $0.01356 |
| Opus 5 | $0.00009 | $0.00678 |
| Sonnet 5 | $0.00004 | $0.00271 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
phren-consolidate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phren-consolidate - Cross-project synthesis
Find patterns across project findings and surface insights that apply everywhere.
Read every project's FINDINGS.md, find patterns that show up across multiple projects, and write them to a shared global findings file.
The point: something you learned on one project probably applies elsewhere. This surfaces those connections.
Prerequisites
This skill needs at least two projects with FINDINGS.md files to be useful. If you haven't captured any findings yet, use add_finding() during a session first.
Works with or without profiles. If profiles are set up, it scans projects in the active profile. If not, it scans all project directories in the phren repo.
When to run
- Monthly, or when the user asks
- After a burst of work across multiple projects
- When starting a new project (to seed it with relevant cross-cutting knowledge)
What to do
1. Find the phren directory
PHREN_DIR="${PHREN_DIR:-$HOME/.phren}"
ls "$PHREN_DIR" 2>/dev/null
If it doesn't exist, tell the user:
"No phren directory found at ~/.phren. This skill needs a phren repo with project findings. Run
phren-initto set one up, or set PHREN_DIR if yours is elsewhere."
2. Gather ALL findings
Try the profile-aware path first, fall back to scanning all directories:
MACHINE=$(cat ~/.phren/.machine-id 2>/dev/null || hostname)
# look up profile in machines.yaml to get the project list
# fallback: scan all project directories
FINDINGS_FILES=()
for dir in "$PHREN_DIR"/*/; do
if [ -f "$dir/FINDINGS.md" ]; then
PROJECT_NAME=$(basename "$dir")
FINDINGS_FILES+=("$PROJECT_NAME:$dir/FINDINGS.md")
fi
done
Read every FINDINGS.md file found. Don't sample or skip any. For each file, track which project it came from.
If no FINDINGS.md files exist anywhere, tell the user:
"No FINDINGS.md files found in any project. Use
add_finding()during a work session to start capturing findings."
If only one project has a FINDINGS.md, tell the user:
"Only found findings for . Need at least two projects to find cross-cutting patterns. Use
add_finding()in other projects first."
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 · 153 lines · 18 tokens per session scan A 00fd2a3dcf7c
phren-consolidate is a skill published in the GitHub repository alaarab/phren (4 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 1,356 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 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.