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 agentmods add skills/synaptiai/agent-capability-standard/debug-workflownpx skills add synaptiai/agent-capability-standard --skill debug-workflowgit clone --depth 1 https://github.com/synaptiai/agent-capability-standardWhat 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 | $0.00035 | $0.02317 |
| Opus 5 | $0.00017 | $0.01158 |
| Sonnet 5 | $0.00007 | $0.00463 |
| Haiku 4.5 | $0.00003 | $0.00232 |
Grade A, and why
debug-workflow 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 2d 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 — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent
Run the composed workflow debug-workflow using atomic capability skills to systematically debug code changes with full safety and audit capabilities.
Success criteria:
- Every step output is grounded with evidence anchors
- Safety gates are respected (checkpoint before any mutation)
- All issues are traced to root cause with supporting evidence
- Final result includes complete audit trail
- Rollback pathway documented and verified
Compatible schemas:
reference/workflow_catalog.yaml
Inputs
| Parameter | Required | Type | Description |
|---|---|---|---|
goal |
Yes | string | The debugging objective (e.g., "identify why tests fail after refactor") |
scope |
Yes | string|array | Files, directories, or components to investigate |
constraints |
No | object | Hard limits (e.g., time budget, files to exclude, severity threshold) |
prior_context |
No | object | Previous debugging attempts or known information |
Procedure
-
Create checkpoint marker if mutation might occur:
- Create
.claude/checkpoint.okafter confirming rollback strategy
- Create
-
Invoke
/inspectand store output asinspect_out- Examine the scope for symptoms, error patterns, recent changes
-
Invoke
/searchand store output assearch_out- Find related code, error messages, similar patterns
-
Invoke
/map-relationshipsand store output asmap-relationships_out- Map dependencies, call graphs, data flows
-
Invoke
/model-schemaand store output asmodel-schema_out- Model the expected vs actual behavior
-
Invoke
/critiqueand store output ascritique_out- Critically analyze hypotheses, identify weak points
-
Invoke
/planand store output asplan_out- Create remediation plan with verification criteria
-
Invoke
/act-planand store output asact-plan_out- Execute the fix with checkpoint protection
-
Invoke
/verifyand store output asverify_out- Confirm fix addresses root cause
What ships with it
5 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.
- 2d ago First seen · 293 lines · 35 tokens per session scan A 06fc6dc59365
debug-workflow is a skill published in the GitHub repository synaptiai/agent-capability-standard (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 35 tokens to every session and 2,317 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 2026-08-31.
Other skills, from other repositories
write-unit-tests
Writing unit and integration tests for the tldraw SDK. Use when creating new tests, adding test coverage, or fixing failing tests in packages/editor or packages/tldraw. Covers Vitest patterns, TestEditor usage, and test file organization.
hugging-face-dataset-creator
Create and manage datasets on Hugging Face Hub. Supports initializing repos, defining configs/system prompts, and streaming row updates. Designed to work alongside HF MCP server for comprehensive dataset workflows.
design-taste
Stops AI from generating boring, generic UI. Use when building new interfaces, reviewing generated UI, or fixing the flat / generic look that AI tools default to. Anti-slop design principles for premium frontends.
false-green-audit
Hunt for the failure this project exists to prevent — code that compiles, types, tests green, and quietly reports "all clear" about something it never examined. Use when reviewing a release, auditing a subsystem, or before tagging.
scope-discipline
Keep one task closed-looped before starting the next. Triggered when a new problem surfaces mid-task (a bug, a security finding, a missing env var), when you're about to branch into unrelated work, or when you notice the session has sprawled across many half-finished threads. Prevents the "nothing ever lands" failure…
agentfootprint
Use when building AI agents with agentfootprint — LLMCall, Agent, skills, RAG, memory, control flow, Swarm concepts, mock/anthropic/openai/ollama providers, tools, recorders, resilience, and streaming. Also use when someone asks how agentfootprint works or wants to understand the framework.