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 skills/reflexioai/claude-smart/sync-agent-instructionsnpx skills add ReflexioAI/claude-smart --skill sync-agent-instructionsgit clone --depth 1 https://github.com/ReflexioAI/claude-smartWhat 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 | $0.00062 | $0.00298 |
| Opus 5 | $0.00031 | $0.00149 |
| Sonnet 5 | $0.00012 | $0.00060 |
| Haiku 4.5 | $0.00006 | $0.00030 |
Grade A, and why
sync-agent-instructions 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 yesterday.
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:
- sync-agent-instructions — 88% identical, 6 lines differ
What it actually says
Sync Agent Instructions
Keep CLAUDE.md, GEMINI.md, and AGENTS.md in sync so all AI coding tools share the same project instructions.
Workflow
-
Detect changes — Run
git diff HEAD -- CLAUDE.md GEMINI.md AGENTS.mdto see which file(s) have uncommitted changes. -
Determine source file:
- One file changed — That file is the source. Copy its content to the other two.
- Multiple files changed — Ask the user which file to use as the source.
- No files changed — Compare all three with
diff. If they differ, report which sections differ and ask the user which file to use as source. If identical, report "All instruction files are in sync." and stop.
-
Sync — Read the source file and write its exact content to the other two files.
-
Stage — Run
git addon the two modified files. -
Report — Tell the user which file was the source and that the other two have been updated.
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.
- yesterday First seen · 24 lines · 62 tokens per session scan A 1a7b4e9d1d7a
sync-agent-instructions is a skill published in the GitHub repository ReflexioAI/claude-smart (774 stars, last pushed 3d ago), licensed Apache-2.0. It adds 62 tokens to every session and 298 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
reflexio-embedded
Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…
reflexio-consolidate
Run a full-sweep consolidation over all .reflexio/ files — TTL sweep + n-way cluster merge. Use when the user asks to 'clean up reflexio', 'consolidate memory', 'deduplicate playbooks', or suspects drift across sessions.
reflexio
When to use: Always active. This skill is the contract between you and the reflexio cross-session memory plugin.
learn
When to use: The user wants immediate extraction of skills/preferences from the current session — e.g., after a major correction, before context compaction, or to test the loop.
clear-all
When to use: The user explicitly asks to delete all locally-stored skills/preferences. This is destructive and unrecoverable.
show
When to use: The user wants to see what reflexio currently knows about this project.