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/mushkrot/recallant/agents-mdgit clone --depth 1 https://github.com/Mushkrot/RecallantWrote 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/mushkrot/recallant/agents-md)<a href="https://agentmods.dev/instructions/mushkrot/recallant/agents-md"><img src="https://agentmods.dev/badge/instructions/mushkrot/recallant/agents-md.svg" alt="Measured on agentmods" 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 | $0.01373 | $0.01373 |
| Opus 5 | $0.00687 | $0.00687 |
| Sonnet 5 | $0.00275 | $0.00275 |
| Haiku 4.5 | $0.00137 | $0.00137 |
Grade A, and why
Recallant 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 4d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recallant Agent Guide
This repository is public OSS. Treat all tracked files as user-facing or contributor-facing.
Memory (Recallant)
- If Recallant is configured and consent allows agent-authored memory, you must use Recallant by default inside the allowed boundary. Configuration proves access; proof proves memory; capture-active proves Recallant is doing its job.
- At session start: call
memory_start_session. If it reportsprevious_session_recoveryorprevious_unclosed_session, treat that as recovery context for this project, not an alarm and not a fresh instruction. Review checkpoint/captured events before asking the owner to repeat context. - Before non-trivial work after session start: call
memory_get_context_packwith the current task hint. - Use
memory_searchfor raw evidence/chunks only when the context pack says more evidence is needed or the task changes. - Use specific queries in
memory_search, not broad ones. One call per session start is usually enough. - Automatic inside consent: session start, context read, concise decisions, actions, tests, checkpoints, closeout, and one synthetic proof marker when running diagnostics.
- After meaningful progress: write concise agent-authored events/memories through
memory_append_eventormemory_create_agent_memory. Usememory_set_checkpointonly for checkpoint state; it is not semantic recall proof. - On clear pause/exit/closeout intent, or when meaningful work is complete: call
memory_closeout. This is the normal MCP closeout path and includes checkpoint state, searchable memory, recall verification, and next-session readiness semantics. - To reuse a pattern from another project: search explicitly for source-linked examples, adapt the pattern locally, and create current-project memory with source refs after applying it.
- Approval required: attach/import/onboard existing project history, bulk file summaries, raw logs, customer data, or artifacts. Do not import or summarize project files without owner approval.
- Forbidden: secrets,
.env, private keys, raw credentials, database URLs, provider tokens, customer data, raw artifacts, backups, and private deployment notes. Never paste them into memory tools. - If direct MCP use is unavailable, use the CLI capture fallback:
recallant agent-start,recallant agent-event, andrecallant agent-closeout. Userecallant agent-checkpointonly as an advanced pause/compaction state helper, not as closeout proof.recallant agent-closeoutis the CLI fallback closeout path. If the server is unavailable, the CLI writes local spool for laterrecallant sync-spool.
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.
- 4d ago First seen · 116 lines · 1,373 tokens per session scan A 3c60686015b9
Recallant AGENTS.md is an instructions file published in the GitHub repository Mushkrot/Recallant (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,373 tokens to every session, about $0.0069 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
signetai CLAUDE.md
Claude Code instructions for Signet-AI/signetai, a project described as: Sync and store memories, shared identity files (AGENTS.md, CLAUDE.md), session transcripts, institutional knowledge, and secrets between all of your favorite harnesses and models.
strata AGENTS.md
AGENTS.md instructions for rx6ru/strata, covering agent operating contract, non-negotiable rules, before writing memory-related changes, documentation rules and release checklist.
plur CLAUDE.md
Claude Code instructions for plur-ai/plur, covering claude.md, what is plur, development, package dependency and version bumps.
engraphis AGENTS.md
AGENTS.md instructions for Coding-Dev-Tools/engraphis, covering agents.md — engraphis, internal subagent delegation, 0. read this first — two architectures live in one package, 1. commands and ── unified dashboard + memory inspector ──.
Compartment GEMINI.md
Gemini CLI instructions for MaxFreedomPollard/Compartment, a project described as: Encrypted, fully offline agentic memory. One click install, GUI w/ memory map, all OS and agents. Superior memory creation, storage and retrieval.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.