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 commands/aavaz-ai/enterpret-claude-plugins/digestgit clone --depth 1 https://github.com/aavaz-ai/enterpret-claude-pluginsWrote 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/aavaz-ai/enterpret-claude-plugins/digest)<a href="https://agentmods.dev/commands/aavaz-ai/enterpret-claude-plugins/digest"><img src="https://agentmods.dev/badge/commands/aavaz-ai/enterpret-claude-plugins/digest.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 | $0.00031 | $0.02973 |
| Opus 5 | $0.00015 | $0.01486 |
| Sonnet 5 | $0.00006 | $0.00595 |
| Haiku 4.5 | $0.00003 | $0.00297 |
Grade A, and why
digest 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 — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/digest
Build and deliver a recurring customer feedback digest from Enterpret's Wisdom Knowledge Graph. Interactive setup on first run, headless execution for scheduling.
Pre-Flight
- Check if
context/organization.jsonexists. If not, tell the user to run/startfirst. Stop. - Call
get_organization_detailsfrom theenterpret-wisdom-mcpMCP server. If auth fails, tell the user to run/start. Stop. - Read
context/organization.jsonfor org name, slug, and citation base URL.
Skills (reference during execution, not upfront)
wisdom-kg— read if a query fails or schema details are neededwisdom-slack-digest— read when executing the digest (run/preview modes)evidence-synthesis— read if the user wants richer narrative in quotes
Query Rules (critical)
- Always use
LIMIT(max 50) - Count with
COUNT(DISTINCT fi.feedback_record_id)— neverCOUNT(nli) - Never use
countas an alias (reserved word) — usevolume - Sentiment values:
"Positive","Negative","Neutral" - Dates: string comparison on
record_timestamp(notdate()) - Parameter:
cypher_queryforexecute_cypher_query - If no results, say so — never fabricate data
Mode Detection
| Input | Mode | What Happens |
|---|---|---|
/digest (no config exists) |
Setup | Interactive wizard |
/digest (config exists) |
Run | Execute digest and deliver |
/digest setup |
Setup | Force re-enter setup wizard |
/digest run |
Run | Execute digest (error if no config) |
/digest preview |
Preview | Dry run — show formatted output in chat |
/digest config |
Show Config | Display current config and offer to edit |
Setup Mode
A guided, conversational experience that helps the user design a feedback digest and set up recurring delivery. The flow is: understand goals → design content → preview → choose delivery → schedule.
Phase 1: Welcome and Context
Start with a warm, clear explanation of what we're building:
Let's build your feedback digest
I'll help you create a recurring customer intelligence briefing — a snapshot of what your customers are saying about the topics that matter to you.
Here's how this works:
- We'll pick your topics — what feedback themes should this track?
- I'll show you a preview — so you can see exactly what the output looks like
- You'll choose where it goes — Slack, email, or right here in CoWork
- We'll put it on autopilot — recurring delivery on your schedule
Let's start with what matters to you.
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 · 348 lines · 31 tokens per session scan A 1aa88a886e17
digest is a command published in the GitHub repository aavaz-ai/enterpret-claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 2,973 once invoked, about $0.0002 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.