pstack

A structured engineering mode for investigating, building, reviewing, and shipping code changes with a short checklist and real verification.

In plain words
What is it for?
Use it for implementation, debugging, code review, and release tasks that benefit from a small, explicit working process.
Why use it?
It keeps nontrivial coding work focused and requires checking the actual result before calling it finished.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/tellahq/opensession/pstack
Any agent
npx skills add tellahq/opensession --skill pstack
Clone the repo
git clone --depth 1 https://github.com/tellahq/opensession

Made for: Claude Code, Codex.

Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,002 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00037 $0.01002
Opus 5 $0.00018 $0.00501
Sonnet 5 $0.00007 $0.00200
Haiku 4.5 $0.00004 $0.00100

Measured 2d ago against content hash 032357c67e1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pstack 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 2d 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.

.agents/skills/pstack/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pstack mode

Treat the text after /pstack as the task. Pstack mode remains enabled for later turns in this Open Session session. /pstack off disables it. /poteto-mode is the longer name for the same mode.

This is the Open Session adaptation of pstack's Poteto Mode. It keeps the methodology, but uses Open Session's policy-gated tools and isolated child sessions instead of Pi extension tools. Higher-priority Open Session, repository, and user instructions always win. This mode never grants tools, credentials, or permission for external actions.

Start

For every nontrivial task:

  1. Inspect the current checkout and any partial work before proposing changes.
  2. Name the task shape and choose one playbook below.
  3. Keep a short checklist. Include skipped playbook steps with the reason when a step does not apply.
  4. State the data shape or invariant before changing code.
  5. Finish the promised work and verify the real artifact before reporting completion.

Do not turn a small task into ceremony. The smallest coherent process that produces trustworthy evidence is the goal.

Principles

Apply only principles that affect a real decision. Do not list principles decoratively in the final reply.

  • Subtract first. Delete or reuse before adding a layer, abstraction, compatibility path, or dependency.
  • Model the domain. Prefer a table, state machine, typed model, reducer, registry, or clear ownership boundary over scattered conditionals and coupled booleans.
  • Design from the requirement. Integrate the requirement as if it had existed from the start instead of bolting on a side path.
  • Keep boundaries strict. Validate external data at the edge. Keep internal logic typed and direct.
  • Separate writers. Give concurrent workers isolated files, branches, or worktrees before adding locks or coordination.
  • Fix root causes. Reproduce the symptom, trace the mechanism, and change the owning layer. Do not silence it with a guard unless the guard is the domain rule.
  • Sequence verifiable units. Break large work into slices that each end in a meaningful check.
  • Prove behavior. Compilation is supporting evidence. Exercise the user-facing behavior, protocol, output, or measured hot path that changed.
  • Reduce reader load. Prefer fewer layers, less hidden state, and a shorter path from question to answer.
  • Encode repeated lessons. If an instruction is needed twice, consider a test, type, lint, script, or metadata rule instead of more prose.

Read the full file on GitHub · 78 lines

Files

What ships with it

10 files 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.

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. 2d ago First seen · 78 lines · 37 tokens per session scan A 032357c67e1f

Subscribe to this mod's changes

pstack is a skill published in the GitHub repository tellahq/opensession (327 stars, last pushed 2d ago), licensed MIT. It adds 37 tokens to every session and 1,002 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens