pstack is a collection of plain Agent Skills and engineering principles that guide AI-assisted software development across coding agents such as Claude Code, Codex, Pi, Cursor, and OpenCode. It is for developers who want reusable practices for tasks including testing, technical writing, debugging, review, and coordinating agent work. The catalogue entries are the project's skills, agents, and plugin.
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 skills add backnotprop/pstack --skill howgit clone --depth 1 https://github.com/backnotprop/pstackWrote 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/backnotprop/pstack/how)<a href="https://agentmods.dev/skills/backnotprop/pstack/how"><img src="https://agentmods.dev/badge/skills/backnotprop/pstack/how/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/backnotprop/pstack/how"><img src="https://agentmods.dev/badge/skills/backnotprop/pstack/how.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 5.1 | $0.00060 | $0.00763 |
| Opus 5.5 | $0.00024 | $0.00305 |
| Sonnet 5.5 | $0.00012 | $0.00153 |
| Haiku 4.5 | $0.00006 | $0.00076 |
Grade A, and why
how 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 yesterday.
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.
This is a copy
89% identical to how — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
How
Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.
Every spawn is a Task subagent with subagent_type: generalPurpose and readonly: true. Explorers use the how explorer line in the pstack settings file (~/.cursor/rules/pstack-models.mdc in Cursor, ~/.claude/rules/pstack-models.md in Claude Code, ~/.agents/pstack-models.md in other harnesses) (default grok-4.7-xhigh-fast), and every explainer uses the how explainer line (default claude-opus-5-5-xhigh). Set model to that line's value, or to the default if the file or the line is missing. Leave model unset when the value is auto or inherit-parent. If your subagent tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message or your harness's model list. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the poteto-mode skill.
1. Assess complexity
If the scope is ambiguous, state your interpretation and explore. The user can redirect.
- Simple (a single module, a small utility, a narrow question such as "how does function X work"): no explorers. Spawn one explainer that explores and explains in one pass, built from
references/explainer-prompt.mdwithout the explorer-findings section. Go to step 4. - Complex (a subsystem spanning multiple files or services, a cross-cutting feature, a full architectural overview): go to step 2.
When in doubt, take the simple path.
Other harnesses. The spawns in this skill use Cursor's Task tool. In another harness, use its subagent tool: Agent in Claude Code (subagent_type: general-purpose), task in OpenCode (subagent_type: general), spawn_agent in Codex. Keep the prompt and the model. Drop parameters your tool doesn't have. If your harness has no subagent tool, as in Pi without an extension, run each role yourself, one after another.
What ships with it
2 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.
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.
- yesterday Changed a63ac9059796
- 6d ago Changed a2ff24687a40
- 9d ago Changed · -22 lines c80558c167c5
- 13d ago Changed 6039d88a0147
- 17d ago Changed · +2 lines 0958465ec724
- 1mo ago Changed · -76 lines · -4 tokens per session a36197811883
- 1mo ago First seen · 135 lines · 64 tokens per session scan A fe503e7a9b2a
how is a skill published in the GitHub repository backnotprop/pstack (2,498 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 763 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 89% identical to how, differing in 22 lines, and is treated as a copy.
Other skills, from other repositories
analyze-kernel-bottleneck
Systematically identify whether a GPU kernel is compute-bound, memory-bound, or latency-bound using roofline analysis, occupancy calculations, compute/load ratio per tile, and SASS instruction inspection. Produces a decision matrix for optimization strategy selection (cp.async, warp interleaving, tiling…
conduct-empirical-wire-capture
Capture outbound HTTP and telemetry from a CLI harness at runtime. Covers capture-channel selection (transcript file vs verbose-fetch stderr vs outbound proxy vs on-disk state), hook-driven per-event capture vs long-running session capture, JSONL output format for diff-friendly artifacts, and the observability table…
correlate-observability-signals
Unify metrics, logs, and traces for cohesive debugging. Implement exemplars for log-to-trace linking, build unified dashboards using RED/USE methods, and enable rapid root cause analysis across observability signals. Use when investigating complex incidents spanning multiple systems, reducing mean time to resolution…
decode-minified-js-gates
Classify gate call variants in a minified JavaScript bundle. Covers context-window extraction around a flag occurrence, identification of 4–6 reader variants (sync boolean, sync config-object, bootstrap-aware TTL, truthy-only, async bootstrap, async bridge), default-value extraction (boolean / null / numeric /…
chrysopoeia
Extract maximum value from existing code — performance optimization, API surface refinement, and dead weight elimination. The art of turning base code into gold through systematic identification and amplification of value-bearing patterns. Use when optimizing a working but sluggish codebase, refining an API surface…
clean-codebase
Remove dead code, unused imports, fix lint warnings, and normalize formatting across a codebase without changing business logic or architecture. Use when lint warnings have piled up during rapid development, unused imports and variables clutter files, dead code paths were never removed, formatting is inconsistent, or…