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/jmagly/aiwg/ralph-attachnpx skills add jmagly/aiwg --skill ralph-attachgit clone --depth 1 https://github.com/jmagly/aiwgWrote 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/jmagly/aiwg/ralph-attach)<a href="https://agentmods.dev/skills/jmagly/aiwg/ralph-attach"><img src="https://agentmods.dev/badge/skills/jmagly/aiwg/ralph-attach.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 5.1 | $0.00015 | $0.01245 |
| Opus 5 | $0.00008 | $0.00622 |
| Sonnet 5 | $0.00003 | $0.00249 |
| Haiku 4.5 | $0.00002 | $0.00125 |
Grade A, and why
ralph-attach 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 6d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Al Attach
Attach to a running external agent loop and tail its output log in real time. Press Ctrl+C to detach without interrupting the loop.
Natural Language Triggers
Users may say:
- "ralph attach"
- "attach to ralph"
- "follow ralph"
- "watch ralph output"
- "tail the agent loop"
- "stream ralph progress"
Parameters
--loop-id (optional)
The ID of the loop to attach to. If omitted, attaches to the most recently started active loop.
/ralph-attach --loop-id abc123
When multiple loops are active, you must specify --loop-id. Run /ralph-status first to list active loop IDs.
Behavior
When triggered:
- Read
.aiwg/ralph-external/loops/to find active loop state files - If
--loop-idis not provided, select the loop with the most recentstartedAttimestamp that hasstatus: "running" - If no active loop is found, report clearly and exit
- If multiple loops are active and no
--loop-idis given, list them and prompt the user to specify - Resolve the loop's
logFilepath from its state JSON (typically.aiwg/ralph-external/logs/<loop-id>.log) - Begin reading the log file from the current end, streaming new lines as they are appended
- Display each new line to the user as it arrives, prefixed with a timestamp
- Continue until the user presses Ctrl+C or the loop reaches a terminal state (
succeeded,failed,aborted) - On loop completion, print a final status banner and exit cleanly
Output format while tailing:
[10:42:01] Agent loop abc123 — ACTIVE (iteration 3/10)
[10:42:01] Running verification: npm test
[10:42:03] PASS src/auth/auth.test.ts
[10:42:03] Tests: 12 passed, 0 failed
[10:42:04] Iteration 3: VERIFIED — criteria met
[10:42:04] Agent loop: SUCCESS
On loop completion:
═══════════════════════════════════════════
Agent Loop Completed: SUCCESS
Loop ID: abc123
Iterations: 3
Duration: 4m 12s
Report: .aiwg/ralph-external/reports/abc123.md
═══════════════════════════════════════════
Detached from loop abc123.
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.
- 6d ago First seen · 157 lines · 15 tokens per session scan A 7420129cb8a0
ralph-attach is a skill published in the GitHub repository jmagly/aiwg (209 stars, last pushed yesterday), licensed MIT. It adds 15 tokens to every session and 1,245 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 skills, from other repositories
vertical-real-estate
Residential-proptech domain knowledge so architect / pm aren't naive when speccing real-estate products (listings, lead-crm, transaction-coordination, property-mgmt). Codifies MLS/IDX reality, listing status lifecycle + syndication canonical-source, long-cycle lead nurture, transaction-coordination as the high-pain…
skeptical-triage
Reusable 3-round self-challenge + arbiter pattern for filtering false positives from findings/verdicts. Use when the cost of a false-positive gate block exceeds the cost of 4 extra LLM turns.
vertical-hr-recruiting
Domain-knowledge primer for the HR & recruiting vertical (ATS, onboarding, workforce scheduling, engagement). Applied by architect/pm during spec authoring so they aren't naive about hiring pipelines, the admitted offer→onboard data-carry gap, EEO/I-9 compliance, and shift-coverage rules. Stops the four products from…
lifecycle-messaging
Email/SMS lifecycle and deliverability framework for SMB Product-Builder products that send transactional or lifecycle messages (booking reminders, CRM sequences, receipts, win-back). Codifies provider selection (Resend/Postmark/Twilio/SendGrid), domain auth (SPF/DKIM/DMARC), consent and compliance (TCPA, CAN-SPAM…
pm-planning
Decomposition methodology for pm agent — turns an approved ARCH document into a Beads task list with explicit dependencies, time-boxes, and acceptance criteria. The pipeline can only orchestrate work it can see; this skill defines what "seeable work" looks like.
well-architected
6-pillar architecture review framework. Adapted from AWS Well-Architected for use by greatcto's architect agent on every non-nano ARCH document. Forces explicit answers across operational excellence, security, reliability, performance, cost, and sustainability — not just feature design.