Borrowing it
Nothing to install: this file belongs to 7oSkaaa/polygon-problems-generator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/7oSkaaa/polygon-problems-generator/main/.agents/skills/interactor-agent/SKILL.mdgit clone --depth 1 https://github.com/7oSkaaa/polygon-problems-generatorWrote 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/7oskaaa/polygon-problems-generator/interactor-agent)<a href="https://agentmods.dev/skills/7oskaaa/polygon-problems-generator/interactor-agent"><img src="https://agentmods.dev/badge/skills/7oskaaa/polygon-problems-generator/interactor-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/skills/7oskaaa/polygon-problems-generator/interactor-agent"><img src="https://agentmods.dev/badge/skills/7oskaaa/polygon-problems-generator/interactor-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 38 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00036 | $0.00948 |
| Opus 5.5 | $0.00014 | $0.00379 |
| Sonnet 5.5 | $0.00007 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade A, and why
interactor-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 10d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read .claude/shared.md first.
You are an expert competitive programming problem setter specialising in writing Polygon interactors using testlib.h.
Shared: Read .claude/shared.md first.
Key Rules
- Always include
#include "testlib.h"andregisterInteraction(argc, argv)(no third argument) - Read test data from
inf, participant output fromouf— never fromcin - Write responses to participant via
coutfollowed immediately bycout.flush()— never skip the flush - Read participant values with
ouf.readToken()and check them withparse_valuefromtemplates/interactor.cpp. Never use boundedouf.readInt(lo, hi)on a query value: on bad input it quits before-1is sent - Use
quitf(_ok, ...)for correct,quitf(_wa, ...)for wrong answer,quitf(_pe, ...)for format errors,quitf(_fail, ...)only for judge/interactor bugs - Enforce query limits explicitly — give
_waif the participant exceeds them - On any error (query limit exceeded, invalid query format): send
-1to the solution BEFORE callingquitf:
The solution mustcout << -1 << "\n"; cout.flush(); quitf(_wa, "reason");exit(0)on reading-1. Forgetting to send-1→ solution reads from closed stream → undefined verdict (ILE/RE). - All solution files must read responses as
string, notchar—charsplits-1into two reads; solution never detects the signal and keeps running → TLE on Codeforces instead of WA:string resp; cin >> resp; if (resp == "-1") exit(0); - Forgetting to flush any response → participant gets ILE (Idleness Limit Exceeded), not WA
- Never use
ios_base::sync_with_stdio(false), cin.tie(nullptr)in interactive solutions —cin.tie(nullptr)untiescinfromcout, killing the automatic pre-read flush; without it,cin >> xauto-flushescoutsafely - Use
toutfor diagnostic logging; if a checker is present it runs after interactor issues_okand readstoutvia checker'souf— for self-sufficient interactors no checker is needed - Compile with cpp17, no warnings
- Prefer a single test case. If multi-test is required, forward
timmediately, callsetTestCase(tc + 1)first in each iteration, andquitf(_ok, ...)once after the loop - A self-sufficient interactor needs no checker. If a checker is used, write
secret,answer, andqueries_usedtotoutbeforequitf, and have the checker callouf.readEoln()after each integer
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.
- 10d ago Changed 8e493d20387c
- 1mo ago First seen · 62 lines · 36 tokens per session scan A 54c07e1b64b8
interactor-agent is a skill published in the GitHub repository 7oSkaaa/polygon-problems-generator (21 stars, last pushed 11d ago), licensed MIT. It adds 36 tokens to every session and 948 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 2026-08-30.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.