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 OneDro1d/dark-factory --skill context-managementgit clone --depth 1 https://github.com/OneDro1d/dark-factoryWrote 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/onedro1d/dark-factory/context-management)<a href="https://agentmods.dev/skills/onedro1d/dark-factory/context-management"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/context-management/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/onedro1d/dark-factory/context-management"><img src="https://agentmods.dev/badge/skills/onedro1d/dark-factory/context-management.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 | $0.00075 | $0.00522 |
| Opus 5 | $0.00037 | $0.00261 |
| Sonnet 5 | $0.00015 | $0.00104 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
context-management 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 8d 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.
What it actually says
Context Management (analyze once, reuse forever)
Goal: keep .claude/context/ the single, terse, trustworthy memory so agents never re-scan the repo to re-learn what's known. This is the main token-saving lever.
The store
SERVICE-MAP.md— components + flows (one line each).FINDINGS.md— confirmed bugs/root causes (append-only ledger, status-tagged).DECISIONS.md— architecture decisions/rulings (ADR log).<service>/CLAUDE.md— deep per-service detail.- shared-models
CLAUDE.md— contract index.
When to write
- Confirmed root cause → new
F-###in FINDINGS.md (symptom, cause,file:line, status). So it's never re-investigated. - Design/architecture decision → new
D-###in DECISIONS.md (decision, why, source). - New/changed service, routing key, table, object-store key → update SERVICE-MAP.md + the service CLAUDE.md + (if a contract) the shared-models index.
- Status change (OPEN→FIXED) → update the existing entry, don't duplicate.
How to write (compression rules)
- One fact per entry. Cite a source (
file:line, ruling, ticket) for every claim — no guessing. - Prefer tables/IDs over prose. Replace, don't append, when a fact changes.
- If notes have grown long, distill to the durable fact and delete the scratch.
- Keep each context file roughly a screen — if it's growing, compress.
Read-first reminder for every agent
SERVICE-MAP → FINDINGS → DECISIONS → the one relevant CLAUDE.md → source. Stop as soon as you have enough.
Don't
- Don't record session chatter or anything the code/git already states.
- Don't let the store drift from code — if you find a stale entry, fix it (cite the code).
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.
- 8d ago First seen · 36 lines · 75 tokens per session scan A cab5a835ae82
context-management is a skill published in the GitHub repository OneDro1d/dark-factory (0 stars, last pushed today), licensed Apache-2.0. It adds 75 tokens to every session and 522 once invoked, about $0.0004 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 2026-09-01.
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.…
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…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.