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/pehcastro/harness/corpusnpx skills add pehcastro/harness --skill corpusgit clone --depth 1 https://github.com/pehcastro/harnessWrote 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/pehcastro/harness/corpus)<a href="https://agentmods.dev/skills/pehcastro/harness/corpus"><img src="https://agentmods.dev/badge/skills/pehcastro/harness/corpus.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.00537 |
| Opus 5 | $0.00039 | $0.00269 |
| Sonnet 5 | $0.00016 | $0.00107 |
| Haiku 4.5 | $0.00008 | $0.00054 |
Grade A, and why
corpus 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 5d 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
Corpus
reference.md in this directory holds about 150 pairs of real Claude Code chat
output. Each pair is text that Claude produced, followed by the corrected text.
Read the section that matches the mistake. Do not read the whole file.
Sections
| Read this section | When |
|---|---|
| Keep the information | The reply is very short and may drop something the reader needs |
| Do not acknowledge the request | A reply is about to open with "Got it" or "Understood" |
| Do not tell the reader that a point matters | A reply is about to open with "The important thing is" |
| Do not soften a warning | A real risk is about to become "worth knowing" |
| Write the conclusion first | The reasoning is about to arrive before the answer |
| Do not announce a tool call | A sentence describes the tool call that follows |
| Do not repeat work the reader watched | A recap is forming |
| Do not praise an agent, a tool, or yourself | The reply comments on how well the work went |
| Do not write a scorecard | Test counts or progress numbers are forming |
| Do not report that you wait | The reply says "standing by" or "waiting on" |
| Do not repeat a file you just wrote | The reply restates file content |
| Do not repeat tool output | The reply restates command output |
| Do not ask a question that is not a question | A question has an obvious answer |
| Do not hedge, soften, or comment on your own work | A hedge is forming |
| Do not decorate | A table under 4 rows is forming |
| Write each fact one time | The same fact appears twice |
| Do not repeat the request back | The reply quotes the request |
| Do not agree with the reader | The reply opens with "Yes, exactly" |
| Do not offer more work | The reply ends with an offer |
(cut) in the corpus means write nothing. It is not a placeholder.
Notes
The corpus was audited against the banned word list in the Brevity output
style. CHANGES.md records every line the audit changed and why.
What ships with it
2 files 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.
- 5d ago First seen · 43 lines · 78 tokens per session scan A 2bc9418fd11d
corpus is a skill published in the GitHub repository pehcastro/harness (1 stars, last pushed 18d ago), licensed MIT. It adds 78 tokens to every session and 537 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
frontend-design
Guidance for distinctive, intentional frontend/UI design — aesthetic direction, typography, layout, motion, and copy — when building new UI or reshaping existing UI. Gates by scope before designing: a light/surgical change (one component, one page section, extending an existing design system) gets inline design…
docs-consolidate
Audit a repo's documentation for internal contradictions, stale claims, orphans and bloat after it has accumulated commits, then report findings for the user to disposition. Use when the consolidation nudge fires, or when the user asks to consolidate, audit, or spring-clean the docs. Triggers: "/docs-consolidate"…
retro
Run an interactive session retrospective. Reads the per-session event log (maintained by the PostToolUse hook) and uses git diff/status/log as memory primer, then walks through specific moments via adaptive questions driven by what changed, and writes structured native memory entries. Suggest this when the end-of-day…
adr
Use when the user knows what they want built and says "/adr", "write an ADR for X", "decide and build X", or "ADR-driven". Turns an intent into a grounded, cited, build-ready ADR at docs/adr/YYYY-MM-DD- .md — load-bearing decisions surfaced to the human — then hands off to nightshift:plan's landing step (the plan is…
plan
Use when the user has an idea, feature, or fix that is more than a one-sitting edit and says "plan this", "write a plan for X", "/nightshift:plan", or "what would it take to build X". Sizes the work (trivial → no artifact; medium → a lean plan; large → a short spec first), asks one question at a time until the design…
domain-modeling
Use when pinning down domain terminology, building a ubiquitous language or project glossary, disambiguating overloaded or vague terms, or maintaining a CONTEXT.md — or when another skill needs to sharpen the domain model. Do NOT use for recording architectural decisions (use adr) or for writing implementation specs.