Borrowing it
Nothing to install: this file belongs to unnecessary-special-projects/ghist. 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/unnecessary-special-projects/ghist/main/AGENTS.mdgit clone --depth 1 https://github.com/unnecessary-special-projects/ghistWrote 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/unnecessary-special-projects/ghist/agents-md)<a href="https://agentmods.dev/instructions/unnecessary-special-projects/ghist/agents-md"><img src="https://agentmods.dev/badge/instructions/unnecessary-special-projects/ghist/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/unnecessary-special-projects/ghist/agents-md"><img src="https://agentmods.dev/badge/instructions/unnecessary-special-projects/ghist/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 | $0.00369 | $0.00369 |
| Opus 5.5 | $0.00148 | $0.00148 |
| Sonnet 5.5 | $0.00074 | $0.00074 |
| Haiku 4.5 | $0.00037 | $0.00037 |
Grade A, and why
ghist 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- ghist CLAUDE.md — 100% identical, 0 lines differ
What it actually says
Ghist — Project Memory
This project uses ghist for persistent project state.
Required: Run ghist status at the start of every session.
Workflow Rules
- Save plans to the task as soon as they're ready:
cat <<'EOF' | ghist task update <id> --plan-stdin - Keep the plan current — update it on every meaningful change as work progresses.
- Write implementation notes on the task when work is complete — append a
## Implementation Notessection to the plan via--plan-stdin. - Ask the user before closing a task — never auto-close.
Quick Reference
ghist task list— see all tasksghist task add "title"— create a taskghist task update <id> --status in_progress— update statusghist task update <id> --plan-stdin— save or update a plan (pipe via stdin)ghist log "message"— record a decision or noteghist skills show <name>— read detailed skill instructions
Available Skills
ghist skills show context-sync— session start/end protocolghist skills show task-workflow— find → plan → execute → complete loop (statuses: todo, in_planning, in_progress, done, blocked)ghist skills show auto-completion— auto-detect task completionghist skills show log-thinking— log decisions and reasoningghist skills show commit-link— link git commits to tasks automatically
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.
- 2mo ago First seen · 29 lines · 369 tokens per session scan A d7f8f9ea9572
ghist AGENTS.md is an instructions file published in the GitHub repository unnecessary-special-projects/ghist (174 stars, last pushed 8mo ago), licensed MIT. It adds 369 tokens to every session, about $0.0015 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 2026-08-30.
ghist AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ghist AGENTS.mdunnecessary-special-projects/ghist | Instructions file | 174 | 8mo ago | MIT | A | 369 | 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 |