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.
git clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/summon)<a href="https://agentmods.dev/commands/athola/claude-night-market/summon"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/summon/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/commands/athola/claude-night-market/summon"><img src="https://agentmods.dev/badge/commands/athola/claude-night-market/summon.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 | $0.00028 | $0.00740 |
| Opus 5 | $0.00014 | $0.00370 |
| Sonnet 5 | $0.00006 | $0.00148 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
summon 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 7d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
summon
Launch the egregore to autonomously process work items
through planning, implementation, testing, and PR
creation. By default the egregore runs indefinitely,
scanning for new work after completing its current
manifest. Use /egregore:dismiss to stop it.
Invoke Skill(egregore:summon), which carries the orchestration loop, the
manifest mode, the pipeline mapping, the context-overflow and token-budget
protocols, the progress monitoring and the failure handling.
When To Use
- You have one or more issues or tasks to process without manual intervention.
- You want to run a multi-hour or multi-day development pipeline overnight or over a weekend.
- You want the agent to self-recover from crashes and rate limits via the watchdog.
- You want continuous autonomous processing that finds and handles new work as it appears.
When NOT To Use
- For quick, single-file changes. Just do them directly.
- When you need tight human-in-the-loop review at every step. Use normal Claude sessions instead.
- On repositories you do not trust the agent to modify. Egregore creates branches and opens PRs autonomously.
Usage
From a prompt:
/egregore:summon "Refactor the auth module to use JWT"
From GitHub issues by number:
/egregore:summon --issues 42,43,44
From GitHub issues by label:
/egregore:summon --issues-label "egregore"
Bounded mode (stops when time window expires):
/egregore:summon --bounded --window 2d --issues 42,43,44
Options
| Option | Default | Description |
|---|---|---|
<prompt> |
none | Free-text work description |
--window |
5h |
Time window (e.g. 5h, 7d) |
--bounded |
false | Stop when time window expires |
--issues |
none | Comma-separated issue numbers |
--issues-label |
none | GitHub label to pull issues |
The egregore runs indefinitely by default. Pass
--bounded to set a hard time limit. In both modes,
the egregore scans for new work after completing all
current items. The only difference is that bounded mode
exits when the time window expires.
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.
- 7d ago First seen · 102 lines · 28 tokens per session scan A a1a7ccbed257
summon is a command published in the GitHub repository athola/claude-night-market (337 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 740 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 2026-09-03.
Other commands, from other repositories
contact-upsert
Create or update a contact, optionally assign to groups.
github-issue-fix
This is a detailed way you can analyze the GitHub issues and let Claude handle them in best possible way.
spec
A requirements-planning command for OpenSpec, a tool that records software changes as proposals, specification updates, and task lists. It clarifies the request, challenges risky assumptions, and pauses for approval before implementation.
start
Analyze this project and build a GoalT goal tree for it, linking real files and backend artifacts to each goal.
features:status
(Features) Show implementation status by phase.
features:add
(Features) Add a new feature to a specific phase.