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/ssx360/matrixscroll/agents-mdgit clone --depth 1 https://github.com/SSX360/matrixscrollWhat 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 | $0.00621 | $0.00621 |
| Opus 5 | $0.00311 | $0.00311 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade A, and why
matrixscroll AGENTS.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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Prose rules for this repository live in CLAUDE.md. Read it before
writing or editing any user-facing text. The condensed version:
- Active voice, sentence-case headings, present tense, second person.
- Every paragraph must name something a reader could look up.
- No em-dashes (—) and no en-dash separators ( – ). Use a hyphen, comma, period, or parentheses.
- One negative-parallelism construction per page, maximum.
- Banned: seamless, cutting-edge, robust, game-changer, unleash, elevate, next-gen, revolutionize, delve, tapestry, leverage, harness, empower.
- Naming DORA, PCI DSS, the EU AI Act, SOC 2, NIST, the SSDF, or the FS-AI RMF obliges the file to carry "evidence mapping, not a certification claim". Never assert that anything is certified or compliant.
- The published version is
0.7.0, perpyproject.tomlandhttps://pypi.org/pypi/matrixscroll/json. Pin it explicitly in every install example. Unreleased tree changes may retarget the software PQC default toml-dsa-87; do not claim that default on PyPI until the release that ships it. - SSX360 produces the SE050 USB signer and supplies it through direct inquiry. Distinguish direct-contact availability from self-service or retail distribution.
- Never delete or soften a "Verification boundaries" section.
- Do not claim CNSA 2.0 certification, FIPS CMVP validation, or NSA approval. Naming ML-DSA-87 as the Category 5 / CNSA 2.0 signature parameter set is parameter readiness only.
Commit attribution
Commit envelopes detect actor_type and tool from the environment, so a
commit you make is recorded as agent with your tool name. Do not set
MATRIXSCROLL_ACTOR_TYPE=human to make a range look human-authored, and do not
edit or re-sign an envelope that is already published. See
docs/explanation/actor-attribution.md.
Run vale --minAlertLevel=error before you start and again before you finish.
The linter gets the last word, never the model. The full guide is the
ssx360-prose Skill and
docs/explanation/style-supplement.md.
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 · 50 lines · 621 tokens per session scan A 5cb5c318d408
matrixscroll AGENTS.md is an instructions file published in the GitHub repository SSX360/matrixscroll (5 stars, last pushed 9d ago), licensed Apache-2.0. It adds 621 tokens to every session, about $0.0031 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 2026-08-31.
Other instructions, from other repositories
ai-supply-chain-guard AGENTS.md
Instructions for ZarK/ai-supply-chain-guard, covering supply chain guard and public metadata hygiene.
warrant AGENTS.md
Instructions for s0fractal/warrant, covering agent & contributor conduct (governance-critical), hard rules, the human's role and precedent (why this file exists).
agent-runtime-proof AGENTS.md
AGENTS.md instructions for fantasyce/agent-runtime-proof, covering agent runtime proof project rules, product boundary, version 1 scope, evidence rules and authoritative design.
aguara CLAUDE.md
Instructions for garagon/aguara, covering claude.md, project status, build & test commands, single package test and single test function.
grove CLAUDE.md
Instructions for jmilinovich/grove, covering grove, architecture rules, running locally, code conventions and what not to do.
atrib CLAUDE.md
Instructions for creatornader/atrib, covering atrib: the protocol for verifiable agent actions, what this is, repository structure, hub doc and authoritative docs.