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 agentmods add instructions/objectstack-ai/objectstack/claude-mdgit clone --depth 1 https://github.com/objectstack-ai/objectstackWhat 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 | $0.01397 | $0.01397 |
| Opus 5 | $0.00698 | $0.00698 |
| Sonnet 5 | $0.00279 | $0.00279 |
| Haiku 4.5 | $0.00140 | $0.00140 |
Grade A, and why
objectstack CLAUDE.md 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 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.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
AGENTS.md is the source of truth for working in this repo — read it. Its Prime Directives are binding. Do not rely on this file alone; the four rules that must never be missed are inlined here because missing any one of them wastes or corrupts other agents' work.
⛔ Claim the issue before you write any code
Assign the issue to yourself (gh issue edit <n> --add-assignee @me, or issue_write with
assignees) as the first action of the task — before the worktree, before the first read.
Several agents work this repo at once and an unassigned issue reads as an open invitation: two
that start on it burn the same hours twice, then race to land conflicting shapes. Already
assigned to someone else? It is taken — pick another or ask; never reassign it. File findings
unassigned when only recording; assign at the moment you start.
All agents share one GitHub identity, so the assignee field can't tell you whether a claim
is yours — a claim is assign plus a claim comment with your session ID and branch
(claude/issue-<n>-<slug>), and before writing code you must re-read the comments: an
earlier claim with a different session ID means it's taken, whatever the assignee says.
(Skipping that read is how one issue got implemented twice in one morning.)
⛔ Worktree-first — before your FIRST file edit (AGENTS.md Prime Directive #11)
This repo — and every sibling repo you touch (objectui, cloud) — is edited by
multiple agents at once. The shared primary checkout has its HEAD switched and its
tree reset under you, silently clobbering uncommitted work. A feature branch on the
shared checkout is NOT enough — it still gets switched under you. You MUST be in a
dedicated per-task worktree:
git fetch origin main && git worktree add --no-track ../<repo>-<task> -b <branch> origin/main && cd ../<repo>-<task> && pnpm install
Then make all edits there. This applies per repo: if a task spans framework and
objectui, create a worktree in each. Two PreToolUse hooks enforce this, and both check
the target file's own repo (so sibling repos are covered): guard-main-checkout.sh
blocks Edit/Write/NotebookEdit, and guard-main-checkout-bash.sh blocks the same
write as a Bash command (>/>>, sed -i, perl -i, tee, cp, mv, rm,
touch) — reads are never blocked, and anything it cannot parse confidently is allowed
through, so the rule still outranks the hook. Non-task exception (both hooks, one switch):
OS_ALLOW_MAIN_EDITS=1. Follow the rule because it's correct, not because the hook fires.
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.
- 2d ago First seen · 87 lines · 1,397 tokens per session scan A 0ed7e666cd1a
objectstack CLAUDE.md is an instructions file published in the GitHub repository objectstack-ai/objectstack (45 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,397 tokens to every session, about $0.0070 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 2026-08-30.
Other instructions, from other repositories
bkn-foundry AGENTS.md
AGENTS.md instructions for openbkn-ai/bkn-foundry, covering agents.md, read before doing anything, hard rules for agents and commits & branches.
octo-cli CLAUDE.md
Instructions for Mininglamp-OSS/octo-cli, covering claude.md — octo-cli project instructions, what is octo-cli, architecture, identity model and command structure (12 active domains, 308 operations).
ontology-atlas AGENTS.md
Instructions for wlsdks/ontology-atlas, covering agents.md — ontology-atlas, product and non-negotiable architecture, start here, structure and routes and operating gates and skills.
FDEOps AGENTS.md
Instructions for suboss87/FDEOps, covering agents.md - working in the fdeops repository, if you are helping use fdeops in an engagement, if you are contributing to this repository and boundaries.
session-graph AGENTS.md
Instructions for robertoshimizu/session-graph, covering agents.md — project rules, branch and production workflow and change discipline.
ontology-atlas CLAUDE.md
Instructions for wlsdks/ontology-atlas, covering claude.md, visibility and mirrors, claude code loading and synchronization.