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/elnora-ai/elnora-slack/slack-syncgit clone --depth 1 https://github.com/Elnora-AI/elnora-slackWrote 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/elnora-ai/elnora-slack/slack-sync)<a href="https://agentmods.dev/commands/elnora-ai/elnora-slack/slack-sync"><img src="https://agentmods.dev/badge/commands/elnora-ai/elnora-slack/slack-sync.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 | $0.00022 | $0.00608 |
| Opus 5 | $0.00011 | $0.00304 |
| Sonnet 5 | $0.00004 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
slack-sync 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 5d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slack Workspace Sync
Regenerate the workspace reference cache from live Slack data. The cache lets the
slack-messages skill resolve names to IDs without an API round-trip.
Prerequisites
The elnora-slack CLI must be on your PATH (npm install -g @elnora-ai/slack)
and a bot token must be configured (elnora-slack auth test should succeed). If
not, see INSTALL_FOR_AGENTS.md.
Reference cache location
Write the generated files to the first of these that resolves:
$SLACK_REFERENCES_DIR${CLAUDE_PLUGIN_ROOT}/references/
The committed *.template.md files are examples only — never overwrite them.
Write workspace-users.md and workspace-channels.md (gitignored) alongside.
Step 1: Fetch live data (2 parallel Bash calls)
elnora-slack users list --compact
elnora-slack conversations list --types public_channel --compact
Step 2: Read the current cache
Read both in parallel (fall back to the .template.md for the expected shape if
the generated file doesn't exist yet):
workspace-users.mdworkspace-channels.md
Step 3: Diff and update
3a. workspace-users.md — team members
From the users response, keep real humans only:
- Exclude bots (
is_bot: true) - Exclude Slackbot (
id: USLACKBOT) - Exclude deleted/deactivated users (
deleted: true, or name starting withdeactivateduser)
Build the table with: ID, username, real_name, email (from profile). Keep a Quick Lookup section mapping first name → ID and username — this is what the agent uses for fast resolution.
3b. workspace-channels.md — channels
From the conversations response, drop archived channels. Split into:
- Active Channels — internal channels (sorted by name)
- External Channels — channels whose name starts with
ext- - Routing — map topics to channel names for quick agent routing
Update the *Generated: YYYY-MM-DD* line.
Step 4: Report changes
## Slack Sync Complete
**Updated:** YYYY-MM-DD
### Changes detected
- X new users (names)
- Y users removed (names)
- Z new channels (names)
- N channels archived (names)
### Files updated
- [ ] workspace-users.md
- [ ] workspace-channels.md
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.
- 5d ago First seen · 87 lines · 22 tokens per session scan A ebe2d36d2b7e
slack-sync is a command published in the GitHub repository Elnora-AI/elnora-slack (1 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 608 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 commands, from other repositories
carryover
Write a structured session carryover so a fresh session resumes without losing context.
describe
Write the searchable vocabulary this repository does not contain — agent-authored descriptions for undescribed declarations, the single biggest lever on retrieval quality.
search
Search this repository in plain language and report the declarations that answer it, each with its file, exact line range and the words it matched on.
index
Index this repository for local RAG search, then report which rung it is on — descriptions still to write, a promotion to apply, or nothing left.
status
Check the health of this repository's RAG index — whether it is stale, how much of it carries written descriptions, and which settings are in force.
verify
Manually run the verifier subagent against a proposed skill. Pass the skill name as $ARGUMENTS. Use this when you want to verify a proposal immediately rather than waiting for an applicable task to come up naturally.