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/samzong/recall/reflectnpx skills add samzong/Recall --skill reflectgit clone --depth 1 https://github.com/samzong/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/skills/samzong/recall/reflect)<a href="https://agentmods.dev/skills/samzong/recall/reflect"><img src="https://agentmods.dev/badge/skills/samzong/recall/reflect.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 | $0.00057 | $0.01014 |
| Opus 5 | $0.00028 | $0.00507 |
| Sonnet 5 | $0.00011 | $0.00203 |
| Haiku 4.5 | $0.00006 | $0.00101 |
Grade A, and why
reflect 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 today.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reflect
Overview
Reflect is the official recall-reflect Recall extension. It is a discussion-first workflow for reviewing AI coding sessions through Recall's stable CLI JSON and JSONL protocol. The extension reconstructs a conversation-first timeline across sessions and surfaces observed patterns as questions for the user, not as automatic conclusions or edits.
Use this skill when the user wants project-level reflection on AI coding process, workflow friction, handoffs, repeated corrections, scope drift, or possible future calibration.
Reflect output is evidence for discussion, not permission to change skills, prompts, configs, instruction files, or project files.
Core Rule
Do not treat an observed pattern as a calibration target, workflow change, or proposal unless the user explicitly confirms the interpretation. Ask first, then act only on confirmed direction.
Scope Defaults
Scope to the current repo unless the user asks otherwise. Resolve the project directory with:
git rev-parse --show-toplevel
Run Reflect with structured output. Prefer user-facing dispatch when the extension is installed and managed by Recall:
recall reflect --project /absolute/project/path --format json
Direct extension invocation is also acceptable when testing or calling the extension binary explicitly:
recall-reflect --project /absolute/project/path --format json
Add --time 30d or --source <source> when the user narrows the review. Use --sync when recent sessions may not be indexed yet.
Workflow
-
Resolve the repo scope.
- Use the repository root for current-repo reflection.
- Use the user-provided path when they specify one.
- Explain the scope briefly if there may be multiple worktrees or project directories.
-
Run Reflect.
- Prefer
recall reflect ...when Recall can dispatch to the installed extension. - Use
recall-reflect ...for direct testing or explicit extension invocation. - Prefer JSON for structured inspection.
- Use text output only when the user wants a human-readable report directly.
- Prefer
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed a735e30f64a9
- 4d ago First seen · 111 lines · 57 tokens per session scan A 1ab46c430af2
reflect is a skill published in the GitHub repository samzong/Recall (79 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 1,014 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
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.
simplicio-learn
Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from…
simplicio-compress
Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is…
simplicio-runtime
Govern and execute Simplicio workflows through native execution, MCP, gates, checkpoints, receipts, backpressure, pools, memory, and subagents. Use when a task needs durable evidence, controlled side effects, native acceleration, MCP compatibility, or Runtime reconciliation. Do not make Loop depend on Runtime for…
axum-test-transport
Choose between in-process tower::ServiceExt::oneshot tests and real tokio::net::TcpListener server tests for Axum services in this repository.
anarlog
Query Anarlog meetings, notes, summaries, transcripts, participants, action items, and recurring history. Use when a user asks about their Anarlog meeting data or needs meeting context for another task.