Borrowing it
Nothing to install: this file belongs to FlineDev/Recall. 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/FlineDev/Recall/main/AGENTS.mdgit clone --depth 1 https://github.com/FlineDev/RecallWrote 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/flinedev/recall/agents-md)<a href="https://agentmods.dev/instructions/flinedev/recall/agents-md"><img src="https://agentmods.dev/badge/instructions/flinedev/recall/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/flinedev/recall/agents-md"><img src="https://agentmods.dev/badge/instructions/flinedev/recall/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 | $0.01491 | $0.01491 |
| Opus 5.5 | $0.00596 | $0.00596 |
| Sonnet 5.5 | $0.00298 | $0.00298 |
| Haiku 4.5 | $0.00149 | $0.00149 |
Grade A, and why
Recall 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recall Plugin
Project Structure
Recall/
├── skills/session/
│ └── scripts/ # Core scripts
│ ├── parse-transcript.py # JSONL → markdown parser (main script)
│ ├── condense-tail.py # Split + combine for large transcripts (>20K tokens)
│ ├── pre-compact.sh # PreCompact hook entry point
│ ├── post-compact.sh # Post-compaction stdout reminder
│ └── session-start.sh # SessionStart hook (cleanup)
├── tests/
│ ├── conftest.py # Shared fixtures, module imports
│ ├── generate_fixtures.py # Generates synthetic JSONL + markdown fixtures
│ ├── fixtures/ # Generated test data (fictional "TaskTracker" project)
│ │ ├── jsonl/ # 16 JSONL transcript variants
│ │ └── markdown/ # 5 parsed markdown variants
│ ├── test_parse_tool_calls.py
│ ├── test_parse_condensers.py
│ ├── test_parse_session.py
│ ├── test_parse_postprocess.py
│ └── test_condense_tail.py # Tests for split/combine logic
├── commands/
│ ├── session.md # /recall:session — manual session recall
│ ├── compact-on.md # /recall:compact-on — enable compaction integration
│ └── compact-off.md # /recall:compact-off — disable compaction integration
└── README.md # User-facing documentation
Architecture: PreCompact writes, CLAUDE.md reads, SessionStart cleans
Claude Code's SessionStart hook stdout is silently dropped (bug).
However, CLAUDE.md IS re-read from disk after every compaction, and @file references are resolved during that re-read.
Hook Flow
- PreCompact hook (
pre-compact.sh):- Parses transcript → generates recall content
- If >20K tokens: condenses with a single
claude -p --model sonnetcall (~30-40s) - Writes result to
.claude/recall-context.mdin the project directory - Also writes to
/tmp/recall-<session-id>.mdas a persistent copy
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 · 126 lines · 1,491 tokens per session scan A 27664c9e29c4
Recall AGENTS.md is an instructions file published in the GitHub repository FlineDev/Recall (10 stars, last pushed 1mo ago), licensed MIT. It adds 1,491 tokens to every session, about $0.0060 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.
Recall AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| Recall AGENTS.mdFlineDev/Recall | Instructions file | 10 | 1mo ago | MIT | A | 1,491 | Claude Code, 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 | yesterday | 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 |