ostk-cache AGENTS.md

Project instructions for ostk-cache, including startup and shutdown commands, file-editing rules, and guidance for renaming modules.

In plain words
What is it for?
Use them when booting the project, diagnosing its tool surface, renaming modules, or making related file and template changes.
Why use it?
They reduce setup mistakes and preserve the project's required kernel state, imports, templates, and verification steps.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/os-tack/ostk-cache/agents-md
Clone the repo
git clone --depth 1 https://github.com/os-tack/ostk-cache

Made for: Codex, OpenCode.

Per session 3,682 This file is loaded in full into every session.
When invoked 3,682 The same file — it is already loaded in full.
Security scan D 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.03682 $0.03682
Opus 5 $0.01841 $0.01841
Sonnet 5 $0.00736 $0.00736
Haiku 4.5 $0.00368 $0.00368

Measured 2d ago against content hash a2a40c6edd2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

ostk-cache AGENTS.md scanned grade D with 2 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 2d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

reap, and stderr separation. Dangerous commands (`rm -rf`, `chmod 777`,

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

reap, and stderr separation. Dangerous commands (`rm -rf`, `chmod 777`,
AGENTS.md · 241 lines

How it starts

The opening of the file, as written. The whole thing — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Kernel

When .ostk/ exists in the project run ostk boot first to load the kernel. Run ostk shutdown (canonical, no kernel prefix) to cleanly terminate.

If ostk help or [ctx] envelopes show fewer resident tools than this doc lists (e.g. bash, fs_ops, read, lock, spawn, interact, tack, help, session missing), the project's .language is stale (pre-→1489 schema, blank column 10). Run ostk mcp diag to confirm, then ostk shutdown triggers the →1597 backfill, OR delete .ostk/.language and re-boot to seed fresh. The fix is in shutdown's compile_language; it is idempotent and silent.

Self-documenting surface (read this when something is missing)

The kernel emits its own canonical reference; trust it over older docs:

  • ostk --agents — agent-facing one-stop guide (syscalls, signals, vocab, do_not)
  • ostk --help — full CLI tree, organized by section: SYSTEM ABI / DAILY WORK / WORK PIPELINE / IDENTITY & SECURITY / RECOVERY & FLEET / DOCUMENTATION & SPECS / INFRASTRUCTURE / DIAGNOSTICS / SYSTEM SETUP
  • ostk <verb> --help — per-verb help (every verb above)
  • ostk mcp diag — verify tool surface integrity (seed × present × core × abi)

The structural split: System ABI verbs (frozen, agent-callable, exposed as MCP tools) live under the SYSTEM ABI section. Operator-overlay verbs (show, work, decide, trace, commit, recall) live under DAILY WORK / WORK PIPELINE — they are CLI-only by design (per →1589 epic). The mcp__ostk__* namespace mirrors the System ABI exactly. If you need a verb that isn't in the MCP namespace, reach for ostk <verb> via bash.

In-flight ABI alignment work: EPIC →1821 (align ABI verb contracts across CLI, MCP, docs, and dispatch) tracks remaining drift between these surfaces. If you hit a kernel verb X has no internal handler or a schema mismatch, check the children of →1821 before fixing locally — several are already filed (→1638 fs_ops dispatch gap, →1820 arrive schema, →1822/→1826 recall surface, →1824 verb_load).

Read the full file on GitHub · 241 lines

Changes

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.

  1. 2d ago First seen · 241 lines · 3,682 tokens per session scan D a2a40c6edd2c

Subscribe to this mod's changes

ostk-cache AGENTS.md is an instructions file published in the GitHub repository os-tack/ostk-cache (9 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 3,682 tokens to every session, about $0.0184 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.