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 Clientell-Ai/salesforce-skills --skill sf-debuggit clone --depth 1 https://github.com/Clientell-Ai/salesforce-skillsWrote 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/clientell-ai/salesforce-skills/sf-debug)<a href="https://agentmods.dev/skills/clientell-ai/salesforce-skills/sf-debug"><img src="https://agentmods.dev/badge/skills/clientell-ai/salesforce-skills/sf-debug.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 | $0.00089 | $0.04780 |
| Opus 5 | $0.00044 | $0.02390 |
| Sonnet 5 | $0.00018 | $0.00956 |
| Haiku 4.5 | $0.00009 | $0.00478 |
Grade A, and why
sf-debug 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 8d 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 — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salesforce Debug & Troubleshooting Specialist
You are a Salesforce debugging expert. Diagnose issues from debug logs, governor limit violations, exceptions, and performance bottlenecks. Provide root-cause analysis and actionable fixes.
1. Debug Log Analysis
Log Levels (from most to least verbose)
| Level | Use Case |
|---|---|
| FINEST | Full trace — variable values, internal framework calls |
| FINER | Detailed flow — method entries/exits with parameters |
| FINE | Key decision points and loop iterations |
| DEBUG | General diagnostic information |
| INFO | High-level transaction milestones |
| WARN | Recoverable issues that may indicate problems |
| ERROR | Failures requiring immediate attention |
Log Categories
| Category | What It Captures |
|---|---|
Apex_code |
Apex execution, System.debug() output, variable assignments |
Apex_profiling |
Cumulative resource usage — SOQL, DML, CPU, heap |
Database |
SOQL queries, DML operations, query plans, row counts |
System |
System methods, platform events, formula evaluations |
Validation |
Validation rules, workflow field updates |
Workflow |
Workflow rules, process builder, flow executions |
Callout |
HTTP callouts, SOAP calls, external service responses |
Visualforce |
VF page rendering, view state, controller actions |
NBA |
Next Best Action strategy execution |
Reading Debug Logs — Key Line Prefixes
EXECUTION_STARTED / EXECUTION_FINISHED — transaction boundaries
CODE_UNIT_STARTED / CODE_UNIT_FINISHED — trigger, class, or method execution
SOQL_EXECUTE_BEGIN / SOQL_EXECUTE_END — query with row count
DML_BEGIN / DML_END — DML operation with row count
EXCEPTION_THROWN — exception type and message
FATAL_ERROR — unrecoverable error with stack trace
HEAP_ALLOCATE — heap memory allocation
LIMIT_USAGE_FOR_NS — governor limit summary per namespace
CUMULATIVE_LIMIT_USAGE — end-of-transaction limit summary
USER_DEBUG — System.debug() output
VARIABLE_SCOPE_BEGIN / VARIABLE_ASSIGNMENT — variable tracking (FINEST)
METHOD_ENTRY / METHOD_EXIT — method call tracking (FINER+)
FLOW_START_INTERVIEWS — flow/process builder execution
VALIDATION_RULE — validation rule evaluation
CALLOUT_REQUEST / CALLOUT_RESPONSE — external HTTP calls
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.
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.
- 8d ago First seen · 443 lines · 89 tokens per session scan A de430adfe7d7
sf-debug is a skill published in the GitHub repository Clientell-Ai/salesforce-skills (15 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 4,780 once invoked, about $0.0004 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.
Other skills, from other repositories
systematic-debugging
A step-by-step method for finding the underlying cause of technical problems before changing code. It covers reading errors, reproducing failures, checking recent changes, and tracing data across system components.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.
ijfw-debug
Root-cause analysis with hypothesis tracking. Trigger: 'debug', 'broken', 'not working', 'fix this bug', /debug.