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 Far-200/think-before-code --skill problem-decodergit clone --depth 1 https://github.com/Far-200/think-before-codeWrote 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/far-200/think-before-code/problem-decoder)<a href="https://agentmods.dev/skills/far-200/think-before-code/problem-decoder"><img src="https://agentmods.dev/badge/skills/far-200/think-before-code/problem-decoder/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/far-200/think-before-code/problem-decoder"><img src="https://agentmods.dev/badge/skills/far-200/think-before-code/problem-decoder.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 | $0.00070 | $0.01542 |
| Opus 5.5 | $0.00028 | $0.00617 |
| Sonnet 5.5 | $0.00014 | $0.00308 |
| Haiku 4.5 | $0.00007 | $0.00154 |
Grade A, and why
problem-decoder 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 1mo 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 — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Problem Decoder
Why this exists
A large share of DSA mistakes are not reasoning errors at all — they are
reading-error: the learner solved a problem slightly different from
the one that was actually asked. dsa-tutor assumes the problem has
already been read correctly and starts from "describe a brute-force
approach." This skill is the step before that: force a precise reading
before any solving instinct kicks in.
This skill never designs an approach, names a pattern, or gives a hint toward a solution. Once the problem is fully decoded, hand the learner back to dsa-tutor.
Circuit breaker
Before letting the conversation move toward "how would you solve this," check silently:
Has the learner stated, in their own words, the input format,
output format, constraints, and at least one non-obvious edge case?
NO → stay here. Ask about the missing piece specifically.
YES → decoding is done. Point them to dsa-tutor for the approach.
Hard stop: if you're about to say "so the approach here would be" or name a pattern — stop. That is not this skill's job.
What to extract
Work through these one at a time, not as a dumped checklist. Ask the learner to state each one first; only add what they missed.
- Input — exact types, shape, and any stated bounds (array length, value range, whether it's sorted, whether values repeat).
- Output — exact format expected, and what "correct" means when multiple valid answers could exist (any valid one? the smallest? in original order?).
- Constraints — the numeric bounds (e.g.
n ≤ 10^5). Ask the learner what those bounds imply about the complexity the problem is expecting — this is a mechanical reading skill most learners skip, and it belongs here, not in complexity-coach (which analyzes an approach the learner already has, not the problem's expected ceiling). - Edge cases — both the ones the statement mentions explicitly
and the ones it implies (empty input, single element, all
duplicates, negative numbers, integer overflow). This is reading
the statement's edges before any solving — constructing a
systematic, executable test suite for an approach the learner
already has belongs to
test-case-coach, not here. - Ambiguities — anything the statement leaves unresolved that the learner needs to decide on (tie-breaking rules, mutability of input, whether order matters).
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.
- 1mo ago First seen · 173 lines · 70 tokens per session scan A 5abab363804e
problem-decoder is a skill published in the GitHub repository Far-200/think-before-code (16 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 1,542 once invoked, about $0.0003 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
interactive-leetcode-mcp
Use when the user wants to practice LeetCode problems, submit solutions, or set up LeetCode integration. Covers MCP server installation, learning-guided practice flow, solution submission, and authentication.
leetcode-helper
Expert LeetCode problem solver for optimized C++ coding interview solutions. Use when: the user pastes a LeetCode problem, asks for an optimized algorithm, wants C++ LeetCode code, needs a dry run, asks for line-by-line explanation, wants a hint before the solution, wants brute force to optimized progression, wants…
configure-profile
Create or update the global learner profile. Interviews the learner using the measurement checklist in references/PROFILE-TEMPLATE.md and writes the structured result to profile/PROFILE.md. Use when a new learner sets up Upstack for the first time, or after completing a course to update skills and Dreyfus levels.
create-course
Scaffold a new course directory from the COURSE.md schema. Creates the directory structure, populates COURSE.md with YAML frontmatter and markdown template sections, and creates stub assignment directories. Use for curated courses (core/courses/) or personal courses (custom/courses/) in any domain.
start-course
Initialise a learning session. Checks for an existing journal in progress/ /journal.md, creates one from the template if missing, loads the course definition, and calibrates to the learner's declared context. Use when starting a new course or resuming after a break.
start-learning-path
Enrol in a curated learning path. Discovers available paths, presents project options in plain language, records the learner's choice, initialises the integration journal, and displays the full course roadmap. Run once at the start of the path — not at the start of each course. Distinguishes enrolment (path level…