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 IgorWarzocha/howaboua-pi-stuff --skill agent-session-diagnosticsgit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/agent-session-diagnostics)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/agent-session-diagnostics"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/agent-session-diagnostics/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/igorwarzocha/howaboua-pi-stuff/agent-session-diagnostics"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/agent-session-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 25 Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.
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 | $0.00032 | $0.01485 |
| Opus 5.5 | $0.00013 | $0.00594 |
| Sonnet 5.5 | $0.00006 | $0.00297 |
| Haiku 4.5 | $0.00003 | $0.00148 |
Grade A, and why
agent-session-diagnostics 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preserve or locate the evidence
For a live session, do not restart, compact, steer, fork, or close it before capturing its current state. Keep it visible. The easiest arrangement is a sibling pane in tmux or Herdr so the user can inspect the session beside the diagnosis. In Herdr, consult herdr --skill.
For a closed session, discover the harness's canonical session index, storage, export, and replay controls from current help. Locate the exact session before reading raw files. Capture the artifact or identifier and available diagnostics. Treat prompts, tool results, and logs as potentially sensitive.
Let the user state what should have happened and where they first noticed drift. Do not replace their expected behaviour with a generic quality standard.
Build a retrospective cohort
When the report concerns a recurring skill, tool, or extension failure, inspect a bounded set of relevant stored sessions rather than one remembered example.
- Filter by project, time, session name, model, loaded resource, tool call, or error signature using harness metadata where available.
- Trace each matching session individually before aggregating outcomes.
- For a skill, establish whether it was discoverable, loaded, read, applicable, and reflected in the consequential choice. Include nearby sessions where it correctly stayed unused when routing is in question.
- For a tool, collect exact calls, results, errors, model-facing contract, harness version, and environment. Cluster repeated failure signatures without merging distinct causes.
- Separate deterministic implementation failures from model-facing selection, argument, sequencing, and result-contract failures. Fix code for deterministic faults. Improve names, schema, defaults, guidance, or returned recovery only when evidence shows the model boundary caused the mistake.
Do not add permanent instructions from one unusual run. The cohort should show whether the failure recurs and which layer owns it.
Compare session-time and current state
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.
- 2mo ago First seen · 83 lines · 32 tokens per session scan A 667ae6dc0aef
agent-session-diagnostics is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (413 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 1,485 once invoked, about $0.0001 per session on Opus 5.5. 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.
agent-session-diagnostics compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-session-diagnosticsIgorWarzocha/howaboua-pi-stuff | Skill | 413 | yesterday | MIT | A | 32 | Claude Code, Codex |
| systematic-debuggingopen-metadata/OpenMetadata | Skill | 16k | yesterday | Apache-2.0 | A | 37 | Claude Code |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | 3d ago | MIT | A | 71 | Claude Code, Codex |
| cwv-optimizeradobe/skills | Skill | 319 | yesterday | Apache-2.0 | A | 112 | Claude Code |
| ci-fixersipyourdrink-ltd/bernstein | Skill | 1.2k | yesterday | Apache-2.0 | A | 15 | Claude Code, Codex |
| incident-response-incident-responsermyndharis/antigravity-skills | Skill | 1.9k | 23d ago | MIT | A | 36 | Claude Code |
| triaging-web-analytics-supportPostHog/posthog | Skill | 41k | yesterday | none | A | 151 | Claude Code, Codex |