Borrowing it
Nothing to install: this file belongs to PurdueRCAC/globus-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PurdueRCAC/globus-mcp/main/.agents/skills/globus-harness/SKILL.mdgit clone --depth 1 https://github.com/PurdueRCAC/globus-mcpWrote 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/purduercac/globus-mcp/globus-harness)<a href="https://agentmods.dev/skills/purduercac/globus-mcp/globus-harness"><img src="https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-harness/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/purduercac/globus-mcp/globus-harness"><img src="https://agentmods.dev/badge/skills/purduercac/globus-mcp/globus-harness.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 | $0.00139 | $0.03409 |
| Opus 5.5 | $0.00056 | $0.01364 |
| Sonnet 5.5 | $0.00028 | $0.00682 |
| Haiku 4.5 | $0.00014 | $0.00341 |
Grade A, and why
globus-harness 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 2mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
globus-harness — apply the self-improvement loop (human-gated)
When to Use
Invoke /globus-harness to turn the harness feedback the lifecycle skills logged into actual
improvements to .agents/ — "a meta feature." It is the deliberate, human-gated act side of an
asymmetric loop: observing friction is cheap (silence-by-default meta-notes in every skill), but acting
on it is careful (fresh eyes, previewed diffs, per-finding commits, a cross-job ledger). This is
meta/maintenance — NOT a lifecycle step: it does not touch product code, GOAL/PLAN/TECH/REVIEW,
or the FSM; it edits the skills, templates, scripts, and docs under .agents/.
Best run after a feature has merged to main (so its META.md is on main and the fix is
unentangled from code review). It can also read a still-open branch's META.md, but such pre-merge
runs are preview-only (--dry-run semantics): the status flips live in a file main does not
have yet, so applying waits for the merge.
Reference: methodology.md ("The self-improvement loop"),
templates/META.md (the finding schema),
harness-log.md (the ledger), AGENTS.md + invariants.md (what may
never be weakened).
Harness portability. Runs on any harness — see factory/portability.md.
Fallbacks: run the Current state commands yourself if not auto-injected; ask in plain text and STOP if
AskUserQuestion is unavailable. git / uv run are portable shell.
User Instructions
Additional instructions provided with the invocation — this is your shaping prompt (which findings matter, what direction to take a fix, what to reject): $ARGUMENTS
Current state (injected at load)
- Branch: !
git branch --show-current - Tree: !
git status --porcelain | head -n 20 - META.md files present: !
ls -1 spec/*/META.md 2>/dev/null - Recent ledger entries: !
tail -n 24 .agents/factory/harness-log.md 2>/dev/null
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.
- 2mo ago First seen · 200 lines · 139 tokens per session scan A 83ee416be1ff
globus-harness is a skill published in the GitHub repository PurdueRCAC/globus-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 139 tokens to every session and 3,409 once invoked, about $0.0006 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.
globus-harness compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| globus-harnessPurdueRCAC/globus-mcp | Skill | 2 | 2mo ago | MIT | A | 139 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |