Menu

Not in the top 1,000 by GitHub stars

tma1-ai/tma1

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

Claude CodeCodexData

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

claude-plugin/codex-skills/tma1-peer/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

claude-plugin/codex-skills/tma1-search/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

claude-plugin/skills/tma1/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

claude-plugin/skills/tma1-peer/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

claude-plugin/skills/tma1-search/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

claude-plugin/skills/tma1-setup/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

server/internal/hooks/codex-skills/tma1-peer/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

server/internal/hooks/codex-skills/tma1-search/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

server/internal/hooks/skills/tma1/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

server/internal/hooks/skills/tma1-peer/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

server/internal/hooks/skills/tma1-search/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

server/internal/hooks/skills/tma1-setup/SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → e95aef8da17c

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit e95aef8da17c8e8a6af6f339cbced3640bf4298d

git clone --filter=blob:none --no-checkout https://github.com/tma1-ai/tma1.git .hotskills/tma1-ai-tma1 && git -C .hotskills/tma1-ai-tma1 checkout --detach e95aef8da17c8e8a6af6f339cbced3640bf4298d # Copy each selected skill directory from .hotskills/tma1-ai-tma1 into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/tma1-ai/tma1.git .hotskills/tma1-ai-tma1 && git -C .hotskills/tma1-ai-tma1 checkout --detach e95aef8da17c8e8a6af6f339cbced3640bf4298d # Copy each selected skill directory from .hotskills/tma1-ai-tma1 into .agents/skills/<skill-name>/
124GitHub stars
1star in 7 days
12skills in this repository
11commits in 30 days

Heat

3.0
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 2, 2026124

30-day change not yet available: not enough history.

Individual skills in this repository

  • tma1-peer claude-plugin/codex-skills/tma1-peer
  • tma1-search claude-plugin/codex-skills/tma1-search
  • tma1 claude-plugin/skills/tma1
  • tma1-peer claude-plugin/skills/tma1-peer
  • tma1-search claude-plugin/skills/tma1-search
  • tma1-setup claude-plugin/skills/tma1-setup
  • tma1-peer server/internal/hooks/codex-skills/tma1-peer
  • tma1-search server/internal/hooks/codex-skills/tma1-search
  • tma1 server/internal/hooks/skills/tma1
  • tma1-peer server/internal/hooks/skills/tma1-peer
  • tma1-search server/internal/hooks/skills/tma1-search
  • tma1-setup server/internal/hooks/skills/tma1-setup

How it works

tma1-peer

When your agent uses it

List recent sessions on this project by agent — peers (Claude Code, Copilot CLI) or your own past sessions. Invoke this skill when the user asks you to read another agent's review feedback, see what someone else tried, act on cross-agent context, or recall your own earlier work here. Trigger phrases: "what did claude do", "what did copilot do", "peer sessions", "cross-agent context", "what did I do earlier", "/tma1-peer".

What it loads into context

Frontmatter

111 tokens

Always available to the agent

SKILL.md

1,320 tokens

When the skill is activated

Reference documents

0 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. Invocation
  2. Normalize the agent name
  3. Flags
  4. Call the tma1 MCP tool
  5. Use the returned content directly
  6. Related tools
  7. Examples

Files

  • ../../../.claude-plugin/marketplace.jsonasset262 bytes
  • ../../.claude-plugin/plugin.jsonasset241 bytes
  • SKILL.mdcore5,227 bytes
Read SKILL.md

# TMA1 Peer-Agent Lens (Codex)

Lists recent sessions on the current project, newest first. Default is
peer agents — the ones that aren't you — because the usual reason to call
this is "Claude Code or Copilot left something here, act on it without me
copy-pasting between terminals". Naming yourself is also allowed.

## Invocation

Auto-selected when the user mentions reading another agent's output on
this project, or typed explicitly:

```
/tma1-peer                          # all peers, latest session each
View the complete source on GitHub

Skills included

  • tma1-peer
  • tma1-search
  • tma1
  • tma1-peer
  • tma1-search
  • tma1-setup
  • tma1-peer
  • tma1-search
  • tma1
  • tma1-peer
  • tma1-search
  • tma1-setup

Repository facts

License
Apache-2.0
Created
Mar 13, 2026
Last pushed
Oct 30, 2026
Forks
16
Open issues
0
Project activity
Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 30 notes
  • claude-plugin/skills/tma1/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • claude-plugin/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • server/internal/hooks/skills/tma1/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • server/internal/hooks/skills/tma1/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • server/internal/hooks/skills/tma1/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • server/internal/hooks/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • server/internal/hooks/skills/tma1-setup/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 81 signals by file

claude-plugin/.claude-plugin/plugin.json

  • Network accessline 4
    "description": "Local-first LLM agent observability powered by GreptimeDB.",   "author": { "name": "killme2008" },   "repository": "https://github.com/killme2008/tma1",
  • Network accessline 5
    "author": { "name": "killme2008" },   "repository": "https://github.com/killme2008/tma1",   "license": "Apache-2.0"
  • Network accessline 6
    "repository": "https://github.com/killme2008/tma1",

claude-plugin/skills/tma1-setup/SKILL.md

  • Broad permissionsline 1
    Bash
  • Network accessline 15
    curl -sf http://localhost:14318/health
  • Network accessline 25
    # macOS / Linux curl -fsSL https://tma1.ai/install.sh | bash
  • Dangerous shell operationline 26
    curl -fsSL https://tma1.ai/install.sh | bash
  • Network accessline 26
    curl -fsSL https://tma1.ai/install.sh | bash
  • Network accessline 30
    # Windows (PowerShell) irm https://tma1.ai/install.ps1 | iex
  • Network accessline 31
    irm https://tma1.ai/install.ps1 | iex
  • Network accessline 56
    # macOS / Linux for i in $(seq 1 30); do   if curl -sf http://localhost:14318/health > /dev/null 2>&1; then
  • Network accessline 57
    for i in $(seq 1 30); do   if curl -sf http://localhost:14318/health > /dev/null 2>&1; then     echo "TMA1 is ready."
  • Network accessline 58
    if curl -sf http://localhost:14318/health > /dev/null 2>&1; then
  • Network accessline 67
    # Windows (PowerShell) for ($i = 0; $i -lt 30; $i++) {   try { if ((Invoke-WebRequest -Uri http://localhost:14318/health -UseBasicParsing).StatusCode -eq 200) { Write-Host "TMA1 is ready."; break } } catch {}
  • Network accessline 68
    for ($i = 0; $i -lt 30; $i++) {   try { if ((Invoke-WebRequest -Uri http://localhost:14318/health -UseBasicParsing).StatusCode -eq 200) { Write-Host "TMA1 is ready."; break } } catch {}   Start-Sleep -Seconds 1
  • Network accessline 69
    try { if ((Invoke-WebRequest -Uri http://localhost:14318/health -UseBasicParsing).StatusCode -eq 200) { Write-Host "TMA1 is ready."; break } } catch {}
  • Network accessline 81
    curl -sf http://localhost:14318/status
  • Network accessline 110
    "CLAUDE_CODE_ENABLE_TELEMETRY": "1",     "CLAUDE_CODE_ENHANCED_TELEMETRY_BETA": "1",     "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:14318/v1/otlp",
  • Network accessline 111
    "CLAUDE_CODE_ENHANCED_TELEMETRY_BETA": "1",     "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:14318/v1/otlp",     "OTEL_EXPORTER_OTLP_PROTOCOL": "http/protobuf",
  • Network accessline 112
    "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:14318/v1/otlp",
  • Network accessline 157
    [otel.exporter.otlp-http] endpoint = "http://localhost:14318/v1/logs"
  • Network accessline 158
    endpoint = "http://localhost:14318/v1/logs"
  • Network accessline 161
    [otel.trace_exporter.otlp-http] endpoint = "http://localhost:14318/v1/traces"
  • Network accessline 162
    endpoint = "http://localhost:14318/v1/traces"
  • Network accessline 165
    [otel.metrics_exporter.otlp-http] endpoint = "http://localhost:14318/v1/metrics"
  • Network accessline 166
    endpoint = "http://localhost:14318/v1/metrics"
  • Network accessline 176
    # macOS / Linux export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:14318/v1/otlp
  • Network accessline 177
    export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:14318/v1/otlp
  • Network accessline 182
    # Windows (PowerShell) $env:OTEL_EXPORTER_OTLP_ENDPOINT = "http://localhost:14318/v1/otlp"
  • Network accessline 183
    $env:OTEL_EXPORTER_OTLP_ENDPOINT = "http://localhost:14318/v1/otlp"
  • Dangerous shell operationline 192
    curl -s -X POST http://localhost:14318/api/query    -H 'Content-Type: application/json'    -d '{"sql": "SHOW TABLES"}' 2>/dev/null | python3 -m json.tool
  • Network accessline 192
    curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 204
    Dashboard: http://localhost:14318
  • Network accessline 206
    Query API — all SQL queries go through POST with JSON body:   curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 207
    curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 211
    OTel endpoint: http://localhost:14318/v1/otlp
  • Network accessline 213
    For more queries: https://tma1.ai/SKILL.md

claude-plugin/skills/tma1/SKILL.md

  • Broad permissionsline 1
    Bash
  • Network accessline 21
    curl -sf http://localhost:14318/health
  • Network accessline 51
    curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 61
    **Important**: The underlying database (GreptimeDB) uses `json_get_string()`, `json_get_int()`, `json_get_float()` for JSON column access. The `->` / `->>` operators are NOT supported. Keys containing dots (like `session.id`) are interprete
  • Network accessline 535
    Remind the user that the full dashboard is available at http://localhost:14318.

server/internal/hooks/skills/tma1-setup/SKILL.md

  • Broad permissionsline 1
    Bash
  • Network accessline 15
    curl -sf http://localhost:14318/health
  • Network accessline 25
    # macOS / Linux curl -fsSL https://tma1.ai/install.sh | bash
  • Dangerous shell operationline 26
    curl -fsSL https://tma1.ai/install.sh | bash
  • Network accessline 26
    curl -fsSL https://tma1.ai/install.sh | bash
  • Network accessline 30
    # Windows (PowerShell) irm https://tma1.ai/install.ps1 | iex
  • Network accessline 31
    irm https://tma1.ai/install.ps1 | iex
  • Network accessline 56
    # macOS / Linux for i in $(seq 1 30); do   if curl -sf http://localhost:14318/health > /dev/null 2>&1; then
  • Network accessline 57
    for i in $(seq 1 30); do   if curl -sf http://localhost:14318/health > /dev/null 2>&1; then     echo "TMA1 is ready."
  • Network accessline 58
    if curl -sf http://localhost:14318/health > /dev/null 2>&1; then
  • Network accessline 67
    # Windows (PowerShell) for ($i = 0; $i -lt 30; $i++) {   try { if ((Invoke-WebRequest -Uri http://localhost:14318/health -UseBasicParsing).StatusCode -eq 200) { Write-Host "TMA1 is ready."; break } } catch {}
  • Network accessline 68
    for ($i = 0; $i -lt 30; $i++) {   try { if ((Invoke-WebRequest -Uri http://localhost:14318/health -UseBasicParsing).StatusCode -eq 200) { Write-Host "TMA1 is ready."; break } } catch {}   Start-Sleep -Seconds 1
  • Network accessline 69
    try { if ((Invoke-WebRequest -Uri http://localhost:14318/health -UseBasicParsing).StatusCode -eq 200) { Write-Host "TMA1 is ready."; break } } catch {}
  • Network accessline 81
    curl -sf http://localhost:14318/status
  • Network accessline 110
    "CLAUDE_CODE_ENABLE_TELEMETRY": "1",     "CLAUDE_CODE_ENHANCED_TELEMETRY_BETA": "1",     "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:14318/v1/otlp",
  • Network accessline 111
    "CLAUDE_CODE_ENHANCED_TELEMETRY_BETA": "1",     "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:14318/v1/otlp",     "OTEL_EXPORTER_OTLP_PROTOCOL": "http/protobuf",
  • Network accessline 112
    "OTEL_EXPORTER_OTLP_ENDPOINT": "http://localhost:14318/v1/otlp",
  • Network accessline 157
    [otel.exporter.otlp-http] endpoint = "http://localhost:14318/v1/logs"
  • Network accessline 158
    endpoint = "http://localhost:14318/v1/logs"
  • Network accessline 161
    [otel.trace_exporter.otlp-http] endpoint = "http://localhost:14318/v1/traces"
  • Network accessline 162
    endpoint = "http://localhost:14318/v1/traces"
  • Network accessline 165
    [otel.metrics_exporter.otlp-http] endpoint = "http://localhost:14318/v1/metrics"
  • Network accessline 166
    endpoint = "http://localhost:14318/v1/metrics"
  • Network accessline 176
    # macOS / Linux export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:14318/v1/otlp
  • Network accessline 177
    export OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:14318/v1/otlp
  • Network accessline 182
    # Windows (PowerShell) $env:OTEL_EXPORTER_OTLP_ENDPOINT = "http://localhost:14318/v1/otlp"
  • Network accessline 183
    $env:OTEL_EXPORTER_OTLP_ENDPOINT = "http://localhost:14318/v1/otlp"
  • Dangerous shell operationline 192
    curl -s -X POST http://localhost:14318/api/query    -H 'Content-Type: application/json'    -d '{"sql": "SHOW TABLES"}' 2>/dev/null | python3 -m json.tool
  • Network accessline 192
    curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 204
    Dashboard: http://localhost:14318
  • Network accessline 206
    Query API — all SQL queries go through POST with JSON body:   curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 207
    curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 211
    OTel endpoint: http://localhost:14318/v1/otlp
  • Network accessline 213
    For more queries: https://tma1.ai/SKILL.md

server/internal/hooks/skills/tma1/SKILL.md

  • Broad permissionsline 1
    Bash
  • Network accessline 21
    curl -sf http://localhost:14318/health
  • Network accessline 51
    curl -s -X POST http://localhost:14318/api/query \
  • Network accessline 61
    **Important**: The underlying database (GreptimeDB) uses `json_get_string()`, `json_get_int()`, `json_get_float()` for JSON column access. The `->` / `->>` operators are NOT supported. Keys containing dots (like `session.id`) are interprete
  • Network accessline 535
    Remind the user that the full dashboard is available at http://localhost:14318.

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Combined signals: 4 facts
Signal confidence: 78 facts

and 28 more

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md claude-plugin/codex-skills/tma1-peer/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md claude-plugin/codex-skills/tma1-peer/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md claude-plugin/codex-skills/tma1-peer/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md claude-plugin/codex-skills/tma1-peer/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

You might also use

paperclipai/paperclip

The open-source app everyone uses to manage agents at work

111.8kGitHub stars

runkids/skillshare

📚 Sync skills, agents, MCP, plugins to all AI CLI tools with one command and simplify team sharing.

2.9kGitHub stars

markfulton/ai-employees

Open source AI Employees. 8 scheduled business roles, 60 routines, on Claude Code and 10 other harnesses. They drive your browser the way you do and improve every run. You own the…

856GitHub stars

swarmclawai/swarmvault

The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal…

733GitHub stars

getcrew44/crew44

Orchestrate a crew of specialist AI agents in one local-first workspace. Each role on its best model, with memory and skills that compound. Free, MIT.

358GitHub stars

Necmttn/ax

the agent experience layer · observability + memory for AI coding agents (Claude Code + Codex) · local-first, typed, yours

122GitHub stars