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 fusengine/agents --skill think-in-codegit clone --depth 1 https://github.com/fusengine/agentsWrote 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/fusengine/agents/think-in-code)<a href="https://agentmods.dev/skills/fusengine/agents/think-in-code"><img src="https://agentmods.dev/badge/skills/fusengine/agents/think-in-code/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/fusengine/agents/think-in-code"><img src="https://agentmods.dev/badge/skills/fusengine/agents/think-in-code.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00031 | $0.01012 |
| Opus 5.5 | $0.00012 | $0.00405 |
| Sonnet 5.5 | $0.00006 | $0.00202 |
| Haiku 4.5 | $0.00003 | $0.00101 |
Grade A, and why
think-in-code 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 6d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The reduction is typically ~60x in tokens consumed versus reading each file individually and tallying manually.
Think-in-Code Skill
Principle
1 Bash script = N Read calls avoided.
When you'd read 10 files sequentially to extract a summary, you waste tokens loading full contents into context. Instead: 1 shell pipeline returns the compact aggregated result.
Heuristic: if your task is "for each file in set, compute/extract X, then aggregate" → write the script. Reserve Read for targeted inspection of a specific file you already know matters.
5 Runnable Patterns
1. File size audit (files over FUSE_SOLID_MAX_LINES)
find . -type f \( -name "*.ts" -o -name "*.tsx" -o -name "*.py" -o -name "*.php" \) \
-not -path "*/node_modules/*" -not -path "*/vendor/*" \
| xargs wc -l 2>/dev/null \
| awk -v max="${FUSE_SOLID_MAX_LINES:?set to the hook ceiling}" '$1 > max && $2 != "total" {print $1, $2}' \
| sort -rn | head -20
2. Multi-grep symbols (compact JSON)
rg --json -g '*.ts' -g '*.tsx' 'export (function|class|const) (\w+)' src/ \
| jq -r 'select(.type=="match") | "\(.data.path.text):\(.data.line_number) \(.data.lines.text)"' \
| head -50
3. Dependencies with versions
# Node
jq -r '.dependencies, .devDependencies | to_entries[] | "\(.key)@\(.value)"' package.json 2>/dev/null
# PHP
jq -r '.require, ."require-dev" | to_entries[] | "\(.key)@\(.value)"' composer.json 2>/dev/null
4. Error log scan
grep -rEn 'ERROR|FATAL|Exception|panic:|stack trace' \
--include="*.log" logs/ 2>/dev/null \
| tail -30
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.
- 6d ago Changed 0548978567d0
- 1mo ago First seen · 97 lines · 31 tokens per session scan A 24dd7079ef3e
think-in-code is a skill published in the GitHub repository fusengine/agents (32 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 1,012 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
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
compound-docs
Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter. Builds institutional knowledge from solved problems. Use when consulting past solutions before investigating new issues.
watch
Observe actual video and sound over the whole file or named ranges, with timestamped evidence and honest coverage. Use complementary playback, listening and targeted frames; return observations without edits or verdicts.