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 mshadmanrahman/pm-pilot --skill meta-observergit clone --depth 1 https://github.com/mshadmanrahman/pm-pilotWrote 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/mshadmanrahman/pm-pilot/meta-observer)<a href="https://agentmods.dev/skills/mshadmanrahman/pm-pilot/meta-observer"><img src="https://agentmods.dev/badge/skills/mshadmanrahman/pm-pilot/meta-observer.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00010 | $0.00587 |
| Opus 5 | $0.00005 | $0.00293 |
| Sonnet 5 | $0.00002 | $0.00117 |
| Haiku 4.5 | $0.00001 | $0.00059 |
Grade A, and why
meta-observer 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meta Observer
Track which skills are used, how well they work, and what patterns emerge.
When to Use
- Explicitly: "observe skills", "skill performance"
- Passively: after any session with 3+ skill invocations
- Periodically: weekly review of skill usage
What to Track
For each skill invocation:
- Skill name: which skill was triggered
- Trigger: what phrase or condition activated it
- Outcome: success, partial, failed
- Corrections: did the user correct the output
- Duration: rough time spent (fast/medium/slow)
Procedure
-
Log Observation Append to
.claude/logs/skill-observations.md:## {date} | Skill | Trigger | Outcome | Corrections | Notes | |-------|---------|---------|-------------|-------| | {name} | {trigger} | {outcome} | {yes/no} | {brief note} | -
Detect Patterns After logging, scan for:
- Skills never used (candidates for removal)
- Skills frequently corrected (need refinement)
- Missing skills (user repeatedly does something manually)
- Trigger mismatches (wrong skill activates)
-
Surface Insights When patterns emerge:
Skill Observations: - {skill} triggered {count} times, corrected {count} times - Pattern: {description of recurring issue} - Suggestion: {improvement recommendation} -
Update Lessons Write significant findings to
tasks/lessons.md:- Skill gaps discovered
- Trigger improvements needed
- Workflow optimizations found
Output Format
Skill Observations (last 7 days):
Most used: orchestrator (8x), tdd-workflow (5x)
Corrected: handoff-doc (2x) - missing file paths
Unused: meta-observer, strategic-compact
Pattern: Users trigger "verify" but mean "tdd-workflow"
Suggestion: Add "verify" as tdd-workflow trigger
Rules
- Never block workflow to observe; logging is lightweight
- Keep observation log append-only (never delete entries)
- Surface insights only when explicitly asked or patterns are strong
- Create
.claude/logs/directory if it does not exist - Observations are internal; never include in external docs
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 · 83 lines · 10 tokens per session scan A ddfb2147a98f
meta-observer is a skill published in the GitHub repository mshadmanrahman/pm-pilot (20 stars, last pushed 2d ago), licensed MIT. It adds 10 tokens to every session and 587 once invoked, about $0.0001 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
build-implementation
Generate context-aware implementation prompts for a selected growth loop. Use when the user says "build", "implement", "generate code", "create prompt", or "how do I build this".
analyze-codebase
Run comprehensive PLG analysis on a codebase to detect tech stack, existing growth features, and revenue opportunities. Use when the user says "analyze", "scan", "audit codebase", or "find growth opportunities".
deploy-telemetry
Set up analytics and tracking infrastructure for growth loops. Use when the user says "deploy telemetry", "set up analytics", "tracking", "events", "push to supabase", or "skene push".
plan-growth-loop
Generate prioritized growth loops with implementation roadmaps based on codebase analysis. Use when the user says "plan", "growth loops", "prioritize", "what should I build", or "roadmap".
validate-loop
Check if growth loop requirements are actually implemented in the codebase. Use when the user says "validate", "check status", "skene status", "is it done", or "verify implementation".
initialize-config
Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".