read-messages

read-messages is a skill for Claude Code from aksika/abtars. It costs 22 tokens per session (344 once invoked), scanned A, original, Apache-2.0.

A read-only tool for listing conversation sessions and displaying their stored messages from the abmind messages database. It can show recent messages in ordinary, machine-readable, or raw form, with secret redaction by default.

In plain words
What is it for?
Use it to find a session, inspect recent messages, investigate missing context, or retrieve a message history for debugging.
Why use it?
It helps recover context when a conversation seems incomplete or when you need to check whether a message was recorded. Because it only reads data, it does not change the live message store.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit Use it to find a session, inspect recent messages, investigate missing context, or retrieve a message history for debugging.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aksika/abtars/read-messages
Install

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.

Any agent
npx skills add aksika/abtars --skill read-messages
Clone the repo
git clone --depth 1 https://github.com/aksika/abtars

Made for: Claude Code.

Wrote 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.

agentmods badge for read-messages

README.md
[![agentmods](https://agentmods.dev/badge/skills/aksika/abtars/read-messages.svg)](https://agentmods.dev/skills/aksika/abtars/read-messages)
Your own site
<a href="https://agentmods.dev/skills/aksika/abtars/read-messages"><img src="https://agentmods.dev/badge/skills/aksika/abtars/read-messages.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 344 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00022 $0.00344
Opus 5 $0.00011 $0.00172
Sonnet 5 $0.00004 $0.00069
Haiku 4.5 $0.00002 $0.00034

Measured 3d ago against content hash 15d345c5a707, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

read-messages 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 3d 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.

templates/skills/read-messages/SKILL.md · 38 lines

What it actually says

Read Messages

Full documentation for abmind messages. Read-only command — safe against a live gateway (WAL concurrent read), never writes.

List sessions (find the right session_id first)

abmind messages

Output: session_id msgs last per session, newest activity first. Telegram sessions look like telegram:<chatId>.

Dump recent messages of a session

abmind messages --session telegram:111 [--tail 50] [--json] [--raw]
  • Default: last 30 messages, newest first, content truncated to 500 chars and secret-redacted
  • --tail N: how many messages (e.g. 100)
  • --json: machine-readable JSON (id, role, content, timestamp, time)
  • --raw: skip secret redaction — only when the user explicitly needs verbatim content

When to use

  • User asks "do you remember what I said 5 minutes ago?" and recent context seems missing
  • Suspected hydration/context failure — verify the messages actually reached the DB
  • Recovery after a faulty session: read back what was said and continue manually
  • Debugging: check whether a turn was recorded at all (message ids, timestamps)

When NOT to use

  • Memory search (facts/decisions) → use the memory-search skill (abmind recall)
  • Reading memory contents → that is abmind recall, not the messages table
Changes

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.

  1. 3d ago First seen · 38 lines · 22 tokens per session scan A 15d345c5a707

Subscribe to this mod's changes

read-messages is a skill published in the GitHub repository aksika/abtars (9 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 344 once invoked, about $0.0001 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 2026-09-05.

Related

Other skills, from other repositories

context-degradation

This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent performance degradation caused by accumulated or conflicting context.

fabioc-aloha/Alex_Skill_Mall · 45 tokens

pipeline-validator

Discovers, triggers, and monitors Azure DevOps pipelines (PR, Buddy Build, Buddy Release) for the current repo and branch. Auto-diagnoses failures from build logs, applies fixes, commits, pushes, and re-triggers until all pipelines pass or max retries reached. Validates PR existence and description completeness.…

rjmurillo/ai-agents · 81 tokens

ai-agents-empirical-probe-toolkit

Prove-it methods for this repo. Six recipes for runtime-contract probes, guard and threshold calibration, eval A/B, docs-vs-reality audits, reproduce-on-main CI triage, and negative-control test design, each with a worked example from repo history. Use when you say probe the runtime contract, calibrate this guard…

rjmurillo/ai-agents · 119 tokens

memory-enhancement

Manage memory citations, verify code references, and track confidence scores. Use when adding citations to memories, checking memory health, or verifying code references are still valid. Use when you say "add a citation", "verify this memory's code refs", "check memory health". Do NOT use for searching or creating…

rjmurillo/ai-agents · 80 tokens

research-and-incorporate

Research external topics, create comprehensive analysis, and incorporate learnings into Serena and Forgetful memory systems. Use when you say "research and incorporate {topic}", "study {topic} and add to memory", "deep dive on {topic}", or "learn about {topic} for the project". Works on external concepts, frameworks…

rjmurillo/ai-agents · 111 tokens

memory-reflexion

Tier 2 episode extraction, the reflexion write path split out of the memory router per ADR-063. Extracts an episode from a completed session log so later sessions can replay what was tried and what it cost. Use when you say extract episode from session, record what happened this session, or re-extract this episode. Do…

rjmurillo/ai-agents · 98 tokens