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 joris887/exosuit --skill debug-sessiongit clone --depth 1 https://github.com/joris887/exosuitWrote 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/joris887/exosuit/debug-session)<a href="https://agentmods.dev/skills/joris887/exosuit/debug-session"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/debug-session/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/joris887/exosuit/debug-session"><img src="https://agentmods.dev/badge/skills/joris887/exosuit/debug-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00020 | $0.02182 |
| Opus 5.5 | $0.00008 | $0.00873 |
| Sonnet 5.5 | $0.00004 | $0.00436 |
| Haiku 4.5 | $0.00002 | $0.00218 |
Grade A, and why
debug-session scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
debug-session
Skill metrics: Emit a start event to the activity log:
echo "{\"type\":\"skill\",\"event\":\"start\",\"skill\":\"debug-session\",\"ts\":\"$(date -u +%Y-%m-%dT%H:%M:%SZ)\"}" >> docs/sessions/.activity-log.jsonl
Debug session for: $ARGUMENTS
Failure State Persistence
At each phase transition, write docs/sessions/.failure-state.md with YAML frontmatter so the Stop hook and /continue can programmatically detect incomplete workflows.
At workflow start (Phase 1 entry):
---
status: active
skill: debug-session
phase: "1"
phase_name: "Root Cause Investigation"
started_at: "[ISO-8601 timestamp from date -u +%Y-%m-%dT%H:%M:%SZ]"
story: "[from $ARGUMENTS — the error description]"
branch: "[from git branch --show-current]"
next_action: "Reproduce error and trace root cause"
files_modified: []
---
## Context
Error: [error description]
Root cause: not yet identified
Hypothesis: none
Fix attempts: 0
Files investigated: [list as investigation proceeds]
At each phase transition: Update the frontmatter fields: phase, phase_name, next_action, and append to files_modified. Update the Context section with investigation progress (root cause, hypothesis, fix attempts).
On successful fix (Phase 5 complete): Delete .failure-state.md — clean state means no failure to recover from.
Phase 1: Root Cause Investigation (MANDATORY)
Do NOT skip this phase. Do NOT jump to a fix.
1a. Understand the Error
- Read the FULL error message — every line, including stack trace
- What is the exact error? (copy it verbatim)
- Where does it occur? (file:line from stack trace)
- When does it occur? (always, intermittently, under specific conditions)
1b. Reproduce Consistently
Run the relevant test or command to reproduce:
# Run the failing test or trigger the error
If it cannot be reproduced, gather more context before proceeding.
What ships with it
4 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.
- 1mo ago First seen · 231 lines · 20 tokens per session scan A e2fc3ccec723
debug-session is a skill published in the GitHub repository joris887/exosuit (8 stars, last pushed 24d ago), licensed MIT. It adds 20 tokens to every session and 2,182 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 2026-08-31.
Other skills, from other repositories
eval-hooks
Audit Claude Code and Codex hooks for validity, safety, and correctness across settings.json, hooks.json, config.toml, plugin, and skill or agent frontmatter hooks. Resolves each command, checks event names, handler types, matchers, exit-code and JSON decision strategy, and timeouts against each host's documented…
check-cache-bugs
Audit Claude Code setup for cache bugs (CC#40524): sentinel, --resume/--continue, attribution header + ArkNill B3/B4/B5.
investigate
Systematic root-cause debugging: find the cause before writing any fix.
qa
Systematic QA testing of a web application: diff-aware, tiered, with fix-and-verify loop.
sandbox-unblock
Diagnostic protocol to run before reporting a sandbox blocker or asking for a configuration change. Eight checks that eliminate false positives, then a report template the person holding the settings can act on. On one measured day, six of eight reported blockers turned out to be false, all from the same handful of…
optimize
Analyze and suggest performance improvements for code, queries, or systems.