Borrowing it
Nothing to install: this file belongs to amirkiarafiei/open-scholar-peer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/amirkiarafiei/open-scholar-peer/main/.agents/skills/kia-context-init/SKILL.mdgit clone --depth 1 https://github.com/amirkiarafiei/open-scholar-peerWrote 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/amirkiarafiei/open-scholar-peer/kia-context-init)<a href="https://agentmods.dev/skills/amirkiarafiei/open-scholar-peer/kia-context-init"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/kia-context-init/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/amirkiarafiei/open-scholar-peer/kia-context-init"><img src="https://agentmods.dev/badge/skills/amirkiarafiei/open-scholar-peer/kia-context-init.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 | $0.00096 | $0.01730 |
| Opus 5.5 | $0.00038 | $0.00692 |
| Sonnet 5.5 | $0.00019 | $0.00346 |
| Haiku 4.5 | $0.00010 | $0.00173 |
Grade A, and why
kia-context-init 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 1mo 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
kia-context-init — fill in the context for the first time
The installer created the files. This fills them in. Run it once per repository.
The one rule
Never write something you do not know. A confidently wrong context file is worse than an empty one, because it gets believed for months. Where you infer, say you inferred. Where you cannot know, leave the placeholder and say why.
Step 1 — work out which situation this is
git rev-list --count HEAD 2>/dev/null || echo 0 # how much history is there
git log -1 --format=%ad 2>/dev/null # how old
Then look at the tree. Two situations:
- New project — little or no code, few commits. Almost everything comes from the conversation.
- Existing project — real code and real history. Most of it comes from reading, some from asking, and one file cannot be recovered at all.
Step 2 — fill what the code can tell you
These need no human input. Read the repository and write them.
| File | Where it comes from |
|---|---|
specs/ARCHITECTURE.md |
Reverse-engineer it — properly. See the recipe below; a stack table and a folder list is a failed pass. |
specs/DESIGN.md |
Reverse-engineer it from the stylesheets, theme file or component library — real token values, not invented ones. If the project has no interface, delete the file rather than filling it with defaults. |
INDEX.md |
Write it last, once you know what the other files actually contain. |
Reverse-engineering ARCHITECTURE.md — the part that goes wrong
The stack and the folder tree are the two cheapest facts in any repository, so a shallow pass always stops there. They are also the two a reader could get for themselves in one command. Gather them first, then keep going. The file's own How deep to go section lists the questions it has to answer; this is where the answers live in a codebase.
| What you are looking for | Where it usually lives |
|---|---|
| The things this system deals with, and how they relate | Data models, schemas, migrations, type definitions. The tables and their foreign keys are the domain model. |
| Anything that moves through states, and who moves it | Status columns and their enums, constants named for states, the functions that write them, and any permission check guarding those writes. Reconstruct the machine — it is the most common thing missing. |
| What the system refuses to do | Validation, constraints, unique indexes, guard clauses, anything that raises or rejects. A refusal is as much a fact as an action. |
| What happens end to end | Entry points — routes, handlers, commands, jobs, event consumers — followed through one full path. End-to-end tests are usually the clearest description of a flow anyone has written down. |
| What it exposes and what it depends on | The public API surface, the events published and consumed, the external services called. |
| Terms an outsider would misread | Names that recur across modules and mean something specific to this domain. |
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.
- 1mo ago First seen · 135 lines · 96 tokens per session scan A 3f95647336b4
kia-context-init is a skill published in the GitHub repository amirkiarafiei/open-scholar-peer (51 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 1,730 once invoked, about $0.0004 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 2026-09-12.
Other skills, from other repositories
mempalace-task
Create, hand off, claim, execute, and close agent tasks through the MemPalace logstream. Use when the user wants to delegate work, prepare a ready-to-paste task for another agent, receive a MemPalace task id, or explicitly launch a supported headless agent in controlled mode.
knowledge-meeting-ingest
Ingest meeting transcripts from any recorder into Knowledge with attendee enrichment, source notes, supported decisions and commitments, and verification of substance and sequence. Summary-only input is not a verified meeting ingestion.
knowledge-automation
Create scheduled Knowledge ingestion automations with a verified worker, private-vault authority, and an end-to-end scheduled run. Use when asked to schedule or repair recurring ingestion from any source.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…