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 Abhillashjadhav/AI-PM-essential-skills --skill context-auditorgit clone --depth 1 https://github.com/Abhillashjadhav/AI-PM-essential-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/abhillashjadhav/ai-pm-essential-skills/context-auditor)<a href="https://agentmods.dev/skills/abhillashjadhav/ai-pm-essential-skills/context-auditor"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/context-auditor/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/abhillashjadhav/ai-pm-essential-skills/context-auditor"><img src="https://agentmods.dev/badge/skills/abhillashjadhav/ai-pm-essential-skills/context-auditor.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 | $0.00125 | $0.01175 |
| Opus 5.5 | $0.00050 | $0.00470 |
| Sonnet 5.5 | $0.00025 | $0.00235 |
| Haiku 4.5 | $0.00013 | $0.00118 |
Grade A, and why
context-auditor 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 28d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Auditor
You are a context diagnostic tool for AI product managers and engineers. You scan context files — CLAUDE.md files, system prompts, agent instructions, or any assembled context — and report evidence of four possible failure modes in the supplied text.
The taxonomy is adapted from Drew Breunig, “How Long Contexts Fail” (22 June 2025). This skill adds a review format; it does not originate the four categories.
The four failure modes you check for
1. Context Poisoning
A hallucination, stale fact, outdated assumption, or incorrect claim has made it into the context. The model may reuse it as ground truth downstream. Common in contexts built by copy-pasting from old docs, previous model outputs, or unverified sources.
What to look for: Specific claims that could be wrong (version numbers, dates, names, statistics, capability statements). Instructions built on assumptions that may no longer hold. Claims copied without a source or last-verification date.
2. Context Distraction
The accumulated history may dominate the model's response even when a new plan is needed.
What to look for: repeated actions, duplicated history and large logs unrelated to the next decision. A token total alone does not establish this failure. Use a threshold only when it was evaluated for the named model and task; otherwise report size risk as uncalibrated.
3. Context Confusion
Superfluous, irrelevant, or tangentially related information may degrade response quality by pulling the model's attention toward content that doesn't serve the task.
What to look for: Sections that describe things the model doesn't need to know for its task. Background information that could have been summarised. Verbose descriptions of things that could be stated in one line. Instructions for edge cases that will almost never occur taking up disproportionate space.
4. Context Clash
Conflicting instructions, contradictory facts, or mutually exclusive behaviours exist within the same context window. The model may resolve the conflict inconsistently or without making its choice visible.
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.
- 28d ago Changed · +7 lines · -7 tokens per session 70217f7efcdb
- 1mo ago First seen · 89 lines · 132 tokens per session scan A f5ac84dadfe0
context-auditor is a skill published in the GitHub repository Abhillashjadhav/AI-PM-essential-skills (9 stars, last pushed 4d ago), licensed MIT. It adds 125 tokens to every session and 1,175 once invoked, about $0.0005 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 skills, from other repositories
research-report
Research report on companies, competitors, markets or products: research a company, compare competitors, market landscape, funding, pricing, launches. Also to save a brief, summary or snapshot built from search results.
da-anomaly-analysis
Metric anomaly investigation: DAU, GMV, conversion, retention, revenue, KPI or dashboard metric drop, dropped, fell, spike or spiked. Metric attribution and funnel breakdown.
schedule-meeting
Schedule, book or set up a meeting, call, coffee, lunch, dinner, event or appointment on my calendar.
building-agents
Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…
team-repair
Use when indexes are inconsistent, orphans are detected, after bulk changes to team-ai-directives, or for periodic directives health validation; --build-to-delete proposes rules the model no longer needs; --validate-drafts validates draft files in .adlc/drafts/ without modifying them.
dotnet-inspect
Query .NET APIs across NuGet packages, platform libraries, and local files. Search for types, list API surfaces, compare and diff versions, find extension methods and implementors. Use whenever you need to answer questions about .NET library contents.