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.
git clone --depth 1 https://github.com/alexmond/alexmskillsWrote 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/commands/alexmond/alexmskills/report-issue)<a href="https://agentmods.dev/commands/alexmond/alexmskills/report-issue"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/report-issue/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/commands/alexmond/alexmskills/report-issue"><img src="https://agentmods.dev/badge/commands/alexmond/alexmskills/report-issue.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 | $0.00015 | $0.01680 |
| Opus 5.5 | $0.00006 | $0.00672 |
| Sonnet 5.5 | $0.00003 | $0.00336 |
| Haiku 4.5 | $0.00002 | $0.00168 |
Grade A, and why
report-issue 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/prompt-coach:report-issue
Help the user file a redacted bug report about a prompt the coach handled badly.
Never file automatically — the user must explicitly confirm the payload before
gh issue create runs.
Step 1 — Read the flagged queue
Read .claude/prompt-coach/candidates.jsonl in the current repo (each line is a JSON entry
with flagged_at, mark_phrase_first_5_words, target_log_line). If it's missing or
empty, tell the user:
No flagged candidates yet. To flag a prompt, say "coach that was wrong" / "coach missed this" / "coach false positive" / "bad nudge" on the turn immediately after a mistreated prompt, and it'll appear here.
Then stop.
Step 2 — Parse each candidate
For each candidate line, parse target_log_line — it's the coach log format:
- [ts] fired=[...] chosen=... positives=[...] mastered=[...] corrected=[...] praise=... outcome=... prompt=«<first 400 chars of the flagged prompt>»
Extract: timestamp, fired rules, chosen rule, positives, corrections, outcome, and
prompt (which is already truncated to 400 chars but IS the flagged content).
Step 3 — Compute a structural signature (PRIVACY-CRITICAL)
For each candidate, run through the shape of the prompt so the report describes it
without leaking it. Compute these locally (python3 -c ... is fine):
- word_count, char_count
- first_5_words only (never more)
- starts_with_action, starts_with_hedge
- has_file_ref, has_ticket_id, has_backticks, has_url
- has_goal_clause, has_guardrail_clause, has_dod_marker, has_format_spec
- is_question
The analyzer has a compute_signature(prompt, corrections) function you can invoke:
python3 -c "
import sys, json
sys.path.insert(0, '<path-to>/plugins/prompt-coach/scripts')
# rename hyphen for import
import importlib.util
spec = importlib.util.spec_from_file_location('ap', '<path-to>/scripts/analyze-prompt.py')
ap = importlib.util.module_from_spec(spec); spec.loader.exec_module(ap)
print(json.dumps(ap.compute_signature('<first 400 chars>', [])))
"
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 Changed e2d79a916d97
- 1mo ago First seen · 198 lines · 15 tokens per session scan A 72deb686296e
report-issue is a command published in the GitHub repository alexmond/alexmskills (10 stars, last pushed 12d ago), licensed MIT. It adds 15 tokens to every session and 1,680 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 commands, from other repositories
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
error-analysis
Analyze errors and incidents to find root causes and fixes.
doctor
Diagnose a broken llm-router setup.
debug
Systematic debugging with automated investigation and 4-phase methodology. Default: inline evidence gathering and diagnosis. --deep: spawns systematic-debugger agent for full autonomous debugging. Use for errors, stack traces, test failures, or unexpected behavior.
verify-upgrade
Verify Spring Boot project upgrade readiness with parallel multi-skill analysis.
types
Debug and fix TypeScript type errors with systematic analysis and expert guidance.