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/algolia/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/commands/algolia/skills/audit-agent)<a href="https://agentmods.dev/commands/algolia/skills/audit-agent"><img src="https://agentmods.dev/badge/commands/algolia/skills/audit-agent/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/algolia/skills/audit-agent"><img src="https://agentmods.dev/badge/commands/algolia/skills/audit-agent.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 | $0.00024 | $0.00708 |
| Opus 5.5 | $0.00010 | $0.00283 |
| Sonnet 5.5 | $0.00005 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
audit-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Agent (zero-cost static audit)
Read an Agent Studio agent's configuration and return a ranked fix list. No
completions, no judge calls, no writes: this costs nothing and should run
before any paid evaluation (/improve-agent).
Load the agent-studio-evaluations skill first. For CLI mechanics (install,
auth, profiles) see the algobot-cli skill; for what a healthy agent looks
like see the algolia-agent-studio skill (its Anti-Patterns section and
references/agent-studio-guide.md).
Step 1: Get the config
Use a live agent id, or a config saved earlier (for example the output of
algobot agents get <AGENT_ID>, or algobot agents export <AGENT_ID> --output agent.json).
Do not paste credentials into the file.
Step 2: Run the audit
SKILL_DIR is the directory containing the agent-studio-evaluations
skill's SKILL.md (wherever your agent installed it); the script lives in its
scripts/ folder.
python3 "$SKILL_DIR/scripts/audit_agent.py" <AGENT_ID>
# or, offline:
python3 "$SKILL_DIR/scripts/audit_agent.py" agent.json
Run it with --help for options. The script only reads; it never patches or
publishes.
Step 3: Read the findings
The script prints a ranked markdown fix list. Defect classes it checks:
| Check | Why it matters |
|---|---|
Backticked identifiers in instructions that match no tools[].name / type or attached index name |
Observed: a prompt named a display tool that was not attached under that name, and a prompt told the agent to search an index or tool that was not attached. The agent cannot follow either instruction. |
Search tool with null searchParameters |
Default retrieval is large (20 full records with highlight and snippet markup), which inflates input tokens and latency. See Integration Facts in the algolia-agent-studio guide. |
max_iterations set to 0 |
0 falls back to the service default (observed); set an explicit value if you want a specific tool-loop budget. |
| Deprecated config keys | Stale keys that agents scaffold 2.1.0 strips (for example enableAlgoliaMcp); remove them from saved configs. |
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.
- yesterday First seen · 59 lines · 24 tokens per session scan A 1ce0e6d147b5
audit-agent is a command published in the GitHub repository algolia/skills (12 stars, last pushed 2d ago), licensed MIT. It adds 24 tokens to every session and 708 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 2026-10-27.
Other commands, from other repositories
screenshot
Screenshot a URL or document and read it visually.
root-cause
Use when any test fails, bug appears, or behaviour surprises you, before proposing a fix - find the cause and prove it, by reading real evidence, tracing bad values back to their origin, comparing against a working case, and testing one hypothesis at a time.
trace-regression
Investigate a newly introduced bug or regression to identify the offending change and formulate a fix.
cleanup
Run a systematic cleanup on the provided code to resolve smells, simplify complexity, and enforce best practices.
gh-resolve-pr
Fix CI and review findings on a GitHub PR, then report readiness.
flutter-build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.