debug-run

A troubleshooting procedure for a failed OpenSDL laboratory run. A run is one recorded attempt to execute a workflow, and simulation is a way to reproduce it without live equipment.

In plain words
What is it for?
Use it to find the first failed task, trace policy and equipment calls, reproduce the problem in simulation, add regression tests, export evidence, and submit a corrected run.
Why use it?
It connects the failure to recorded events instead of relying on guesswork. It also preserves the failed record while creating and checking a repaired replacement run.

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/fl-sean03/opensdl/debug-run
Any agent
npx skills add fl-sean03/OpenSDL --skill debug-run
Clone the repo
git clone --depth 1 https://github.com/fl-sean03/OpenSDL

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 378 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 $0.00035 $0.00378
Opus 5 $0.00017 $0.00189
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 3d ago against content hash 7a390cb75cdf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-run 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (run.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/debug-run/SKILL.md · 40 lines

What it actually says

Debug a failed run

Inputs

  • persisted run identifier
  • manifest path
  • workflow and inputs when a simulation reproduction is possible

Procedure

  1. Run .agents/skills/debug-run/run.sh RUN_ID [MANIFEST].
  2. Run uv run --locked opensdl events --manifest MANIFEST --run-id RUN_ID and identify the first failed task.
  3. Trace the policy decision, lease, adapter call, timeout, retry, and error events.
  4. Reproduce with a simulation manifest when the workflow and inputs are available.
  5. Fix the smallest correct contract, adapter, runtime, storage, or configuration layer.
  6. Add a regression test and a conformance case when an adapter contract changed.
  7. Re-run the simulation and export it with uv run --locked opensdl export RUN_ID --manifest MANIFEST.
  8. Submit a repaired workflow as a new run with opensdl run WORKFLOW --supersedes RUN_ID. A run records the workflow it was asked to execute, so --run-id RUN_ID resumes only the identical definition and is refused for any other; superseding leaves the failed run's record intact and names the replacement on both.
  9. Check propagation impact before completion.

Completion

The cause is tied to persisted evidence, the regression test fails before the fix and passes after it, and the simulation rerun has an exported evidence bundle.

Stop conditions

Stop on ambiguous physical state or when safe recovery needs hold, abort, resume, or reconciliation behavior that the typed interface does not expose. Do not infer physical reversal from database state.

Files

What ships with it

1 file 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. 3d ago First seen · 40 lines · 35 tokens per session scan A 7a390cb75cdf

Subscribe to this mod's changes

debug-run is a skill published in the GitHub repository fl-sean03/OpenSDL (102 stars, last pushed 3d ago), licensed Apache-2.0. It adds 35 tokens to every session and 378 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.