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/squarewavesystems/squarebox/claude-mdgit clone --depth 1 https://github.com/SquareWaveSystems/squareboxWhat 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 | $0.01772 | $0.01772 |
| Opus 5 | $0.00886 | $0.00886 |
| Sonnet 5 | $0.00354 | $0.00354 |
| Haiku 4.5 | $0.00177 | $0.00177 |
Grade B, and why
squarebox CLAUDE.md scanned grade B with 1 finding 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.
Runtime system-binary promotion uses narrowly matched sudo command forms with How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Repository guidance for coding agents and maintainers.
Agent skills
Issue tracker
Engineering issues and PRDs live in this repository's GitHub Issues. See docs/agents/issue-tracker.md.
Triage labels
Triage uses the canonical needs-triage, needs-info, ready-for-agent, ready-for-human, and wontfix roles. See docs/agents/triage-labels.md.
Domain docs
Squarebox uses a single repository context in CONTEXT.md, with decisions in docs/adr/. See docs/agents/domain.md.
Project model
Read CONTEXT.md before changing behavior. The important state split is:
- Workspace: host project tree mounted at
/workspace. - Managed home: named volume mounted at
/home/dev; survives Box replacement. - Box filesystem: disposable image/container state; selected Box-tier packages must be reconciled after replacement.
- Selection: desired optional tools under
/workspace/.squarebox. - Observed state: binaries/configuration actually usable in the current Box.
- Install identity:
<SQUAREBOX_DIR>/.squarebox/install-state, recording runtime, paths, resource ownership, source revision, and image identity. Release pulls use an immutable digest; source builds use a local image ID/ref. - Candidate/Release: one source SHA bound to one multi-architecture image
digest and matched assets in
release.json.
Relevant architecture decisions are in docs/adr/. Do not reintroduce raw-tag
stable discovery, inferred test passes, default reconstruction during uninstall,
or installation after a failed artifact-verification stage.
Build and local validation
set -euo pipefail
mapfile -t test_files < <(
find tests -maxdepth 1 -type f -name 'test-*.sh' -perm -u+x | sort
)
test "${#test_files[@]}" -gt 0
for test_file in "${test_files[@]}"; do "$test_file"; done
docker build --build-arg SQUAREBOX_VERSION=dev -t squarebox:test .
docker run --rm \
-v "$PWD/scripts:/workspace/scripts:ro" \
squarebox:test bash -c 'scripts/e2e-test.sh smoke'
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 · 165 lines · 1,772 tokens per session scan B c3a17a69733e
squarebox CLAUDE.md is an instructions file published in the GitHub repository SquareWaveSystems/squarebox (71 stars, last pushed 11d ago), licensed MIT. It adds 1,772 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
codex-trace AGENTS.md
Instructions for PixelPaw-Labs/codex-trace, covering claude.md, commands, dev, lint and format.
academic-writing-toolkit AGENTS.md
Instructions for yha9806/academic-writing-toolkit, covering academic writing project, skill discovery, project overview, directories and targets.
academic-writing-toolkit CLAUDE.md
Instructions for yha9806/academic-writing-toolkit, covering academic writing project, project overview, directories, targets and reading constraints.
bounded-relay AGENTS.md
AGENTS.md instructions for mohammad19974/bounded-relay, covering repository operating rules, product boundary, before changing code, implementation invariants and quality gates.
Osverse AGENTS.md
AGENTS.md instructions for Oswald-Hao/Osverse, covering osverse repository rules for coding agents and protected-branch workflow.
cogitator AGENTS.md
Instructions for guilhermehto/cogitator, covering agents.md, layout, commands, demo / readme screenshot and conventions.