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 rayapatiranjithai/prompt-analyzer --skill prompt-reportgit clone --depth 1 https://github.com/rayapatiranjithai/prompt-analyzerWrote 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/rayapatiranjithai/prompt-analyzer/prompt-report)<a href="https://agentmods.dev/skills/rayapatiranjithai/prompt-analyzer/prompt-report"><img src="https://agentmods.dev/badge/skills/rayapatiranjithai/prompt-analyzer/prompt-report/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/skills/rayapatiranjithai/prompt-analyzer/prompt-report"><img src="https://agentmods.dev/badge/skills/rayapatiranjithai/prompt-analyzer/prompt-report.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 | $0.00060 | $0.01271 |
| Opus 5 | $0.00030 | $0.00635 |
| Sonnet 5 | $0.00012 | $0.00254 |
| Haiku 4.5 | $0.00006 | $0.00127 |
Grade A, and why
prompt-report 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 11d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
prompt-report — End-of-session prompting summary
You produce a one-shot summary from the data that the analyze-prompt skill has persisted this
session. You do NOT re-analyze prompts and you do NOT modify any data file (read-only).
GATE
Read the session data first. If it is missing or empty, tell the user no prompts have been analyzed
yet this session and to run analyze-prompt first — then stop.
DATA (read-only)
- Data file:
${CLAUDE_PROJECT_DIR}/.prompt-analyzer/${CLAUDE_SESSION_ID}.json
Injected data
!`test -f "${CLAUDE_PROJECT_DIR}/.prompt-analyzer/${CLAUDE_SESSION_ID}.json" && cat "${CLAUDE_PROJECT_DIR}/.prompt-analyzer/${CLAUDE_SESSION_ID}.json" || echo "NO_DATA_YET"`
If NO_DATA_YET, run the GATE fallback above.
List other sessions (for optional cross-session view)
!`ls -1 "${CLAUDE_PROJECT_DIR}/.prompt-analyzer/"*.json 2>/dev/null | grep -v config.json | wc -l`
Computation (from persisted data only)
- avg_score = mean(scores); trend from first_score → latest_score
- requirement_match_rate = requirement_matches / total_prompts × 100
- best prompt = history entry with max score; worst = min score
- focus habit = the
focus_habitfield (the one habit to build); biggest recurring habit = max key inhabit_tally - improvement curve = the scores[] array rendered as a sparkline (▁▂▃▄▅▆▇█ mapped 1–10)
- self-correction rate = total_self_corrections / total_prompts × 100
- efficiency = (1 − est_wasted_tokens / est_prompt_tokens) × 100, shown as %
- est. tokens spent = totals.est_prompt_tokens; est. wasted on redos = totals.est_wasted_tokens (label both "est." — heuristic, not an exact tokenizer)
- time impact (est.) = frame waste in minutes: each self-correction ≈ 1–2 min of rework; report "≈N min lost to redos" and "≈N min saved by your strong prompts" (label "est.")
- cross-session rollup = if the "other sessions" count > 0, note whether the focus habit is improving across sessions (mention it qualitatively; do not read other files unless asked)
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.
- 11d ago First seen · 97 lines · 60 tokens per session scan A 8c1bfc79cf83
prompt-report is a skill published in the GitHub repository rayapatiranjithai/prompt-analyzer (1 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,271 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 2026-08-31.
Other skills, from other repositories
prompt-writer
Write maximally terse agent prompts from scratch. Use when creating agent specs, command prompts, or instruction sets with constitutional governance.
tersify-prompt
Rewrites agent-instruction prompts to be maximally terse while preserving full intent.
prompt-tuning
Tune a prompt, or anything whose quality is measured by non-deterministic model output, without chasing noise - a noise baseline before the first edit, medians over repeated runs, enforcement AFTER generation rather than in the wording. Use when iterating on prompts or model-judged output.
prompt-optimization
Improves LLM-facing context while preserving intent, execution boundaries, and proportional work. Use when creating or reviewing prompts, agent definitions, skill definitions, or other instructions for an LLM.
recipe-eval-prompt
Compares original and optimized prompts through repeated blind paired execution in git worktrees. Use when evaluating prompt improvement effects or learning prompt engineering through concrete examples.
context-engineering
Optimize Claude Code context-window usage for accuracy and cost. TRIGGER when: hitting context limits, structuring prompts for an agent, or trimming what gets injected into a task. SKIP: persisting knowledge across sessions (use agent-memory); semantic recall tuning (use semantic-memory-mcp).