Borrowing it
Nothing to install: this file belongs to tatargabor/set-core. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tatargabor/set-core/main/.claude/skills/set/forensics/SKILL.mdgit clone --depth 1 https://github.com/tatargabor/set-coreWrote 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/tatargabor/set-core/forensics)<a href="https://agentmods.dev/skills/tatargabor/set-core/forensics"><img src="https://agentmods.dev/badge/skills/tatargabor/set-core/forensics.svg" alt="Measured on agentmods" 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 | $0.00050 | $0.00914 |
| Opus 5 | $0.00025 | $0.00457 |
| Sonnet 5 | $0.00010 | $0.00183 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
set:forensics 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 today.
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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/set:forensics — Run forensics
Triage what failed in a completed orchestration run using filtered views over Claude Code session transcripts and orchestration logs.
WARNING — never read raw session jsonl files unbounded. A single session jsonl can exceed 300 KB and a run typically has 50+ sessions. Always go through the CLI's filtered views first; only fall back to raw Read on a specific line range when the CLI has narrowed the suspect.
Triage order
Always follow this sequence:
-
set-run-logs <run-id> discover— confirm the scope of resolved sources. Verify the main session dir and every-wt-<change>worktree dir was found, plus the orchestration dir. -
set-run-logs <run-id> digest— get the error map. Aggregates tool errors, non-zero bash exits, stop-reason anomalies, user interrupts, permission denials, and crash suspects across every session. Output is grouped by change → session → tool with snippets. -
set-run-logs <run-id> session <uuid> --errors-only— for each suspect session in the digest, view its tool-call timeline filtered to errors. Use the short UUID prefix (≥6 chars) from the digest. Only AFTER you've narrowed via this view should you read raw jsonl. -
set-run-logs <run-id> grep <pattern>— targeted probe for a specific error signature across all sessions. Emits ONLY the matchingmessage.contenttext (not raw jsonl lines), so it's safe to use in agent context. Default cap is 50 matches — pass--limitto raise. -
set-run-logs <run-id> orchestration— cross-reference timing. Shows per-change dispatch counts, last gate status, terminal status, gate-outcome counts. Use this to map a suspect session back to its orchestration timeline (when it dispatched, which gate triggered, what the terminal status was). -
Raw jsonl as last resort. If the CLI's filtered views still leave a question unanswered, locate the specific jsonl from
discoveroutput andReadonly the line range you need. NeverReada session jsonl without an offset/limit.
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.
- today First seen · 60 lines · 50 tokens per session scan A dc109012770e
set:forensics is a skill published in the GitHub repository tatargabor/set-core (35 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 914 once invoked, about $0.0003 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 2026-09-06.
Other skills, from other repositories
atmos-introspection
Introspection & Querying: describe/list commands, config filtering, workspace introspection, dependency graphs, YQ integration, --help= scoped CLI help.
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
atmos-lint
Atmos Terraform linting with TFLint: standalone atmos terraform lint, component-aware config discovery and toolchain versions, TFLint rule configuration, and lifecycle hooks/CI findings. Use when configuring, running, debugging, or documenting Terraform/OpenTofu linting in an Atmos project.
atmos-diagnostics
Atmos diagnostics: machine-readable JSONL event streams, diagnostics.enabled/file/includeoutput, subprocess start/end/output events, masking, and debugging Atmos execution.
gh-ci-analyzer
使用 gh CLI 分析 GitHub Actions CI 日志，提供结构化的故障诊断和报告.
environment-diagnostics
Environment variable validation and configuration verification. Checks that required variables are set, config files parse correctly, ports are available, and system dependencies meet version requirements.