Borrowing it
Nothing to install: this file belongs to unbound-force/gaze. 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/unbound-force/gaze/main/AGENTS.mdgit clone --depth 1 https://github.com/unbound-force/gazeWrote 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/instructions/unbound-force/gaze/agents-md)<a href="https://agentmods.dev/instructions/unbound-force/gaze/agents-md"><img src="https://agentmods.dev/badge/instructions/unbound-force/gaze/agents-md/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/instructions/unbound-force/gaze/agents-md"><img src="https://agentmods.dev/badge/instructions/unbound-force/gaze/agents-md.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 | $0.21662 | $0.21662 |
| Opus 5.5 | $0.08665 | $0.08665 |
| Sonnet 5.5 | $0.04332 | $0.04332 |
| Haiku 4.5 | $0.02166 | $0.02166 |
Grade B, and why
gaze AGENTS.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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- deterministic-ai-report-rendering: Made `gaze report` publish a deterministic report that no model can corrupt (specs/040-deterministic-ai-report-rendering/; incident test.yml run 41309423609). Gaze now renders every s How it starts
The opening of the file, as written. The whole thing — 623 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
Gaze is a static analysis tool for Go that detects observable side effects in functions and computes CRAP (Change Risk Anti-Patterns) scores by combining cyclomatic complexity with test coverage. It helps developers find functions that are complex and under-tested — the riskiest code to change.
- Language: Go 1.24+
- Module:
github.com/unbound-force/gaze/v2 - License: Apache 2.0
Core Mission
- Strategic Architecture: Engineers shift from manual coding to directing an "infinite supply of junior developers" (AI agents).
- Outcome Orientation: Focus on conveying business value and user intent rather than low-level technical sub-tasks.
- Intent-to-Context: Treat specs and rules as the medium through which human intent is manifested into code.
Behavioral Constraints
- Zero-Waste Mandate: No orphaned code, unused dependencies, or "Feature Zombie" bloat.
- Neighborhood Rule: Changes must be audited for negative impacts on adjacent modules or the wider ecosystem.
- Intent Drift Detection: Evaluation must detect when the implementation drifts away from the original human-written "Statement of Intent."
- Automated Governance: Primary feedback is provided via automated constraints, reserving human energy for high-level security and logic.
Gatekeeping Value Protection
Agents MUST NOT modify values that serve as quality or governance gates to make an implementation pass. The following categories are protected:
- Coverage thresholds and CRAP scores — minimum coverage percentages, CRAP score limits, coverage ratchets
- Severity definitions and auto-fix policies — CRITICAL/HIGH/MEDIUM/LOW boundaries, auto-fix eligibility rules
- Convention pack rule classifications — MUST/SHOULD/MAY designations on convention pack rules (downgrading MUST to SHOULD is prohibited)
- CI flags and linter configuration —
-race,-count=1,govulncheck,golangci-lintrules, pinned action SHAs - Agent temperature and tool-access settings —
frontmatter
temperature,tools.write,tools.edit,tools.bashrestrictions - Constitution MUST rules — any MUST rule in
.specify/memory/constitution.mdor hero constitutions - Review iteration limits and worker concurrency — max review iterations, max concurrent Swarm workers, retry limits
- Workflow gate markers —
<!-- spec-review: passed -->, task completion checkboxes used as gates, phase checkpoint requirements
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 Changed · +1 lines · +1,046 tokens per session scan A → B 7f14a168ccc2
- 3d ago Changed · +14 lines · +575 tokens per session a441d481f70c
- 5d ago Changed · +4 lines · +1,471 tokens per session 37451bf4f81c
- 6d ago Changed · +2 lines · +1,037 tokens per session 36545e611a6f
- 9d ago Changed · +1 lines · +288 tokens per session 41f39ea457c1
- 18d ago Changed · +2 lines · +592 tokens per session 7b219388beb3
- 24d ago Changed · +21 lines · +215 tokens per session 18bf71fcb6c6
- 28d ago Changed · +22 lines · +177 tokens per session f3eedd6d2266
- 1mo ago Changed · +1 lines · +248 tokens per session df38d8f60cc7
- 1mo ago First seen · 555 lines · 16,013 tokens per session scan A 36dd105c8e33
gaze AGENTS.md is an instructions file published in the GitHub repository unbound-force/gaze (4 stars, last pushed yesterday), licensed Apache-2.0. It adds 21,662 tokens to every session, about $0.0866 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
gaze AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gaze AGENTS.mdunbound-force/gaze | Instructions file | 4 | yesterday | Apache-2.0 | B | 21,662 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |