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 agentmods add skills/drhalto/agentmako/mako-code-intelnpx skills add drhalto/agentmako --skill mako-code-intelgit clone --depth 1 https://github.com/drhalto/agentmakoWhat 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 | $0.00050 | $0.00961 |
| Opus 5 | $0.00025 | $0.00481 |
| Sonnet 5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
mako-code-intel 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 2d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mako Code Intel
Use this skill for static code queries that are best answered by syntax-aware
search or diagnostics. It is not the general repo-orientation skill; use
repo_map through /mako-ai:mako-discovery for that.
Tools
ast_find_pattern
Use for structural code pattern search over indexed TypeScript, TSX, JavaScript, and JSX files.
- Best for finding syntax shapes that text search may miss.
- Use for patterns such as function calls, JSX attributes, hook usage, imports, conditionals, or unsafe constructs.
- Keep searches bounded with focused patterns and file scopes when possible.
- TSX/JSX snippets starting with
{,[, or<also run with parser context, so callers usually do not need to wrap lone object or JSX patterns. CheckpatternAttemptsand matchpatternVariantwhen you need to know whether the original or auto-anchored form matched. - List metavariables in
captureswhen you need captured values returned. - If the result is a false positive that should not recur, use
finding_ackfrom/mako-ai:mako-workflowwith the returnedackableFingerprint.
lint_files
Use for focused lint/static diagnostics against selected files.
- Best after editing files or when reviewing a known suspect area.
- Defaults to compact output; pass
verbosity: "full"ormaxFindingswhen broad diagnostics are actually needed. - YAML rule packs under
.mako/ruleshot-reload in long-running MCP sessions. - For helper-bypass checks, rule packs may declare
canonicalHelperwith a helpersymboland optionalpath; matching files that already reference the helper are suppressed, while bypasses emit producer/consumer context. - Use the returned finding identity/fingerprint when acknowledging reviewed diagnostics.
- Do not use
agent_feedbackto suppress a diagnostic; usefinding_ack.
extract_rule_template
Use after a fix lands and the removed shape should become future project knowledge.
- Pass the local git
fixCommit; optionally passbaseCommit,filePath, andruleIdPrefix. - Treat the returned
draftYamlas a draft. Review broad patterns and caveats before placing it under.mako/rules. - Follow with
rule_pack_validateand a focusedlint_filesrun before relying on the new rule.
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.
- 2d ago First seen · 93 lines · 50 tokens per session scan A 71c4b44c0e59
mako-code-intel is a skill published in the GitHub repository drhalto/agentmako (51 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 50 tokens to every session and 961 once invoked, about $0.0003 per session on Opus 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
ctxo-safe-edit
Use BEFORE editing, renaming, or deleting any function, class, or method, to avoid breaking dependents.
ctxo-understand
Use at the START of any code task (fix, extend, refactor, understand) before reading source files, to orient with ctxo and avoid going in the wrong direction.
ctxo-review-pr
Use when reviewing a PR, a diff, or recent changes, to get a full risk assessment in one call.
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.