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 kostadis/CampaignGenerator --skill campaign-recallgit clone --depth 1 https://github.com/kostadis/CampaignGeneratorWrote 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/kostadis/campaigngenerator/campaign-recall)<a href="https://agentmods.dev/skills/kostadis/campaigngenerator/campaign-recall"><img src="https://agentmods.dev/badge/skills/kostadis/campaigngenerator/campaign-recall/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/kostadis/campaigngenerator/campaign-recall"><img src="https://agentmods.dev/badge/skills/kostadis/campaigngenerator/campaign-recall.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 | $0.00081 | $0.01653 |
| Opus 5.5 | $0.00032 | $0.00661 |
| Sonnet 5.5 | $0.00016 | $0.00331 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
campaign-recall 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign Recall
Answer a campaign question from the play record. zg finds the relevant passages;
you supply the two things vector search structurally cannot: chronological
order, and the ability to say a thing is not recorded.
Why this skill exists
Measured behaviour of zg on a session-summary corpus:
- Excellent at locating facts from a natural-language question. "What happened to Droop the goblin after he fainted" returned the complete answer as hit #1, including a consequence buried in an NPC entry.
- Blind to time. Asked for "the most recent session," it returned session 6 of
11. Similarity ranking cannot read
011-in a filename. - Cannot report absence. Asked about entities that appear nowhere in the corpus, it returned the nearest neighbours anyway — a chapter title line and an unrelated summary — with no signal that nothing matched.
Both gaps are repaired below, deterministically.
What to do
1. Locate the index
zg --status
Run from the summaries directory, or cd to it first. Confirm Coverage is
100% before trusting any answer. A partial index fails silently: queries return
fewer results with no indication files are missing, which is indistinguishable
from "nothing matched."
2. Query
zg "<the user's question, in natural language>" --limit 8 --preview full
- Pass the question close to how the user phrased it. The index is semantic; keyword-ifying it throws away signal.
--preview fullis required. Output defaults tononewhen piped, which returns headings without bodies.- If the first query is thin, reformulate once with different vocabulary rather than many times with the same.
3. Order the hits by session, from the filename
Session files are named NNN[a]-session-<slug>.md. The numeric prefix is the
authoritative chronological order — it is not in the embeddings and not in the
text. Sort hits by it before presenting anything.
001…011sort numerically.- A letter suffix sorts immediately after its number:
003afollows003. - A gap is meaningful, not an error. A file such as
009-session-not-written.mdrecords a session that was never written up — say so rather than silently skipping it. - "Most recent", "latest", "current", "now", "where does this stand" all mean the highest-numbered file that mentions the subject, not the best-ranked hit.
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 · 151 lines · 81 tokens per session scan A a8c5a31f3277
campaign-recall is a skill published in the GitHub repository kostadis/CampaignGenerator (5 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,653 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
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.…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
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…