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 LuisFelipeMoro/Harness-devkit --skill improve-codebase-architecturegit clone --depth 1 https://github.com/LuisFelipeMoro/Harness-devkitWrote 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/luisfelipemoro/harness-devkit/improve-codebase-architecture)<a href="https://agentmods.dev/skills/luisfelipemoro/harness-devkit/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/improve-codebase-architecture/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/luisfelipemoro/harness-devkit/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/luisfelipemoro/harness-devkit/improve-codebase-architecture.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 | $0.00089 | $0.00494 |
| Opus 5.5 | $0.00036 | $0.00198 |
| Sonnet 5.5 | $0.00018 | $0.00099 |
| Haiku 4.5 | $0.00009 | $0.00049 |
Grade A, and why
improve-codebase-architecture 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.
What it actually says
Report findings only — never fix in this skill. Each finding includes severity, location, and a concrete recommendation.
Refactor guard: this skill only reports. Any refactor that follows must be protected by a characterization test first — pin the current observable behaviour with a passing test (it goes RED the moment the refactor changes behaviour), then refactor under green. Never restructure code that has no test covering it; add the test first.
Phase 1 — Map (1 Explore sub-agent, model: haiku)
Input: Working directory. Optionally: focus area. Output: Raw observations list. Boundary: no analysis, no recommendations.
Dispatch one read-only Explore sub-agent using the call template in references/arch-report-reference.md.
Phase 2 — Score
Input: Phase 1 observations. Output: Findings grouped by severity.
| Severity | Examples |
|---|---|
| Critical | Domain logic in HTTP/DB layer; circular imports; unhandled errors on mutation path |
| High | 3+ callers duplicating logic; file >500 lines; cross-feature deep imports |
| Medium | File 300–500 lines; inconsistent patterns; magic values |
| Low | Naming inconsistency; minor duplication; dead code |
Phase 3 — Report
Write HTML report to /tmp/arch-report-<YYYY-MM-DD>.html.
See references/arch-report-reference.md for HTML scaffold.
Print: Architecture report: /tmp/arch-report-<date>.html — N critical, N high, N medium, N low findings.
Phase 4 — Grill (optional)
Offer: "Want to stress-test any finding? Type /grill-me with the finding."
Phase 5 — ADR (optional)
For each Critical/High finding the user wants to address: offer docs/adr/ADR-NNN-title.md.
See references/arch-report-reference.md for the ADR template.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · +5 tokens per session a8147cfc9fbc
- 1mo ago First seen · 44 lines · 84 tokens per session scan A 6f898ad29722
improve-codebase-architecture is a skill published in the GitHub repository LuisFelipeMoro/Harness-devkit (13 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 494 once invoked, about $0.0004 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…