pi-loop-forensics SKILL.md skillB

pi-loop-forensics from dimetron/pi-go is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dimetron/pi-go/pi-loop-forensics@git:20260809.0f4be13

Pins git:20260809.0f4be13 in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
dimetron/pi-go
Path
.pi-go/skills/pi-loop-forensics/SKILL.md
Versions recorded
1
Latest version
git:20260809.0f4be13, committed Aug 9, 2026
Size
8,442 bytes
Repository stars
214
License
MIT

Diagnose pi-go agent loops and degenerate turns — "agent loop aborted", runaway thinking with no tool calls, repeated phrases. Discriminates genuine model repetition collapse from a race, a tool-parse failure, or a too-low guard, and A/B replays a seed session across providers.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Loop Forensics

Use when a run dies with `agent loop aborted: ...`, or a model burns a long turn
thinking without ever calling a tool. This skill decides **why** before anything
is changed: the abort message names a symptom, not a cause.

Sibling skill `pi-check-session-logs` covers *tool call errors*. This one covers
*repetition and runaway turns*. They do not overlap.

## Where the evidence lives

| What | Path |
|---|---|
| Session logs (JSONL, one per run) | `~/.pi-go/log/<yyyy-mm-dd>/session-HH-MM-SS.log` |
| Session state (resumable) | `~/.pi-go/sessions/<id>/` — `events.jsonl`, `meta.json`, `trajectory.atif.json` |
| Detector source | `internal/tui/agent_loop.go` |

Log rows are `{"time","type","content",...}` with `type` in `session_start`,
`thinking`, `llm_text`, `tool_call`, `tool_result`, `user`, `error`. The model
name is on the `session_start` row — always record it, findings are per-model.

## How the guard actually works

`stuckDetector` (`internal/tui/agent_loop.go:119`) has three independent arms:

- `observe` — identical consecutive tool calls, trips at `maxRepeatToolCalls`=10.
  Pagination args are stripped first (`volatileToolArgs`), so paging one file
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dimetron/pi-go/pi-loop-forensics@sha256:c1f16ec5158ee410

The line at the top of this page pins the label git:20260809.0f4be13, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ws3mpbwswvftjiby.svg)](https://markdownregistry.com/a/art_ws3mpbwswvftjiby)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Aug 9, 2026.

versioncommittedcommitsizeaudit
git:20260809.0f4be13 latest2026-08-09 0f4be13 8,442 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No link to a raw IP address (matched: http://127.0.0.1:11434)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8442 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

dimetron/pi-go · 214 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ws3mpbwswvftjiby
GET https://markdownregistry.com/api/v1/resolve?ref=dimetron/pi-go/pi-loop-forensics
GET https://markdownregistry.com/api/v1/blob/c1f16ec5158ee41093d7da403ccf20c888f828cc57d0ba9120aa5ff863ad97ac

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dimetron/pi-go

AGENTS.md@.pi-go AGENTS.md file
dimetron/pi-go · .pi-go/AGENTS.md
git:20260828.5d00de5 · audit A · 214 stars
bubbletea-testing SKILL.md skill
dimetron/pi-go · .pi-go/skills/bubbletea-testing/SKILL.md · Use this skill whenever writing tests for Bubble Tea (charmbracelet/bubbletea) TUI applications in Go. Triggers include…
git:20260317.b03b37b · audit A · 214 stars
check-linters-before-commit SKILL.md skill
dimetron/pi-go · .pi-go/skills/check-linters-before-commit/SKILL.md · Before any commit, run linters, vet, tests, and build verification; do not commit until checks pass
git:20260827.17116f1 · audit A · 214 stars
code-guidelines-go SKILL.md skill
dimetron/pi-go · .pi-go/skills/code-guidelines-go/SKILL.md · Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or…
git:20260827.17116f1 · audit A · 214 stars
code-review-codex SKILL.md skill
dimetron/pi-go · .pi-go/skills/code-review-codex/SKILL.md
git:20260410.1cba699 · audit C · 214 stars
code-review-pi SKILL.md skill
dimetron/pi-go · .pi-go/skills/code-review-pi/SKILL.md · Review code for quality, run linters, check test coverage, fix issues, and enforce gates. Save the final report to…
git:20260410.d823448 · audit A · 214 stars
demo-subagents-tui SKILL.md skill
dimetron/pi-go · .pi-go/skills/demo-subagents-tui/SKILL.md
git:20260410.d823448 · audit C · 214 stars
design-review SKILL.md skill
dimetron/pi-go · .pi-go/skills/design-review/SKILL.md · Deep design review of Go codebase — naming, structure, consistency, interfaces, error handling. Scores each dimension…
v1.1 · audit A · 214 stars
go-127 SKILL.md skill
dimetron/pi-go · .pi-go/skills/go-127/SKILL.md · What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when…
git:20260919.7d49ee6 · audit A · 214 stars
memory-mine SKILL.md skill
dimetron/pi-go · .pi-go/skills/memory-mine/SKILL.md · Mine project files or conversations into the MemPalace memory system. Indexes source code and conversation history as…
v1.0 · audit A · 214 stars
memory-status SKILL.md skill
dimetron/pi-go · .pi-go/skills/memory-status/SKILL.md · Show MemPalace memory system status — drawer counts, wings, rooms, knowledge graph stats, and embedding model state.
v1.0 · audit A · 214 stars
nightly-session-watch SKILL.md skill
dimetron/pi-go · .pi-go/skills/nightly-session-watch/SKILL.md · Nightly sweep of the last 24h of pi-go sessions — anomalous runs, loop aborts, tool error rates, token waste, real…
git:20260814.704f449 · audit A · 214 stars

Every file in dimetron/pi-go

Browse by kind, by grade B, or by owner.