Borrowing it
Nothing to install: this file belongs to gabrielmahia/civic-agent-kit. 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/gabrielmahia/civic-agent-kit/main/AGENTS.mdgit clone --depth 1 https://github.com/gabrielmahia/civic-agent-kitWrote 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/gabrielmahia/civic-agent-kit/agents-md)<a href="https://agentmods.dev/instructions/gabrielmahia/civic-agent-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielmahia/civic-agent-kit/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/gabrielmahia/civic-agent-kit/agents-md"><img src="https://agentmods.dev/badge/instructions/gabrielmahia/civic-agent-kit/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 | $0.00392 | $0.00392 |
| Opus 5.5 | $0.00157 | $0.00157 |
| Sonnet 5.5 | $0.00078 | $0.00078 |
| Haiku 4.5 | $0.00039 | $0.00039 |
Grade A, and why
civic-agent-kit 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 9d 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.
What it actually says
AGENTS.md — CivicAgentKit
Python SDK for East African civic AI.
Structure
src/civic_agent_kit/data.py— data loaderssrc/civic_agent_kit/agents.py— BudgetAgent, RightsAgent, DroughtAgentsrc/civic_agent_kit/utils.py— KenyaCounties, KiswahiliTranslator
Rules
- Never fabricate civic data
- All data must cite sources with DOIs
- MCP/A2A extras are optional installs
Coverage-Adaptive Reasoning v2
For consequential research, recommendations, investigations, analogy searches, forecasting, opportunity discovery, and canon building:
- A correct ranking inside an incomplete universe is still a failed answer.
- Separate candidate generation from candidate ranking.
- Materiality-gate the search: use the minimum useful set of orthogonal retrieval routes that could change the answer.
- Before closure ask what correct answer the current search method would be structurally incapable of finding.
- Treat aliases, language/geography, era, source class, format, genealogy, taxonomy, legal identity vs operational control/economic benefit, intermediaries, schema categories, null/failure cases, and negative space as potential blind spots when material.
- Maintain leading + competing + null explanations.
- Distinguish answer confidence from coverage confidence.
- “Nothing found” is not evidence of absence when coverage is low.
- Stop when additional independent search routes no longer materially change the candidate universe, hypotheses, decision, or next test.
- When an important miss occurs, repair the retrieval architecture via MISS → SENSOR REDESIGN; do not merely append the missed example.
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.
- 9d ago Changed · +19 lines · +284 tokens per session 93109dc5cc00
- 2mo ago First seen · 14 lines · 108 tokens per session scan A 4fb6766bbff5
civic-agent-kit AGENTS.md is an instructions file published in the GitHub repository gabrielmahia/civic-agent-kit (1 stars, last pushed yesterday), licensed MIT. It adds 392 tokens to every session, about $0.0016 per session on Opus 5.5. 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.
civic-agent-kit AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| civic-agent-kit AGENTS.mdgabrielmahia/civic-agent-kit | Instructions file | 1 | yesterday | MIT | A | 392 | 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 |