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 NexaDuo/mARC --skill upstreamgit clone --depth 1 https://github.com/NexaDuo/mARCWrote 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/nexaduo/marc/upstream)<a href="https://agentmods.dev/skills/nexaduo/marc/upstream"><img src="https://agentmods.dev/badge/skills/nexaduo/marc/upstream/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/nexaduo/marc/upstream"><img src="https://agentmods.dev/badge/skills/nexaduo/marc/upstream.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 | $0.00083 | $0.01298 |
| Opus 5 | $0.00042 | $0.00649 |
| Sonnet 5 | $0.00017 | $0.00260 |
| Haiku 4.5 | $0.00008 | $0.00130 |
Grade A, and why
upstream 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 yesterday.
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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/marc:upstream — upstream process improvements & field lessons
You are running the mARC upstream contribution workflow (persona: @scribe). Your job
is to help the team in a consuming repository capture high-value operational lessons, rule
refinements, or bugfixes discovered in the field and contribute them back to the upstream
mARC product repo — safely, sanitarily, and with explicit human opt-in.
Operating Invariant: Context Gating & Zero Leakage
- Self-improvement is context-gated — no autonomous upstream writes. When mARC runs installed in a user's repository, product-level improvements must NEVER be pushed autonomously. All upstream contributions are opt-in, human-approved, and strictly sanitized before submission. (origin: #46 · 2026-07-06)
- Hard Anti-Anchoring & Genericization Gate. Every candidate rule or improvement destined for upstream must be 100% stack-agnostic. Remove all references to the consuming repository's stack, company name, private service names, internal URLs, credentials, and internal issue numbers. (origin: #66 · 2026-07-09)
- Nothing is transmitted or written silently. You MUST present the exact sanitized diff and commit message to the user and obtain an explicit confirmation before creating any branch, issue, or pull request on the upstream repository. (origin: #46 · 2026-07-06)
Operating Loop
Step 1 — Harvest Candidate Lessons
Scan the current workspace for process adaptations and emergent operational rules:
- Local Governance & Config: Read
${{{ project_dir_env }}:-$PWD}/AGENTS.mdand${{{ project_dir_env }}:-$PWD}/{{ agents_dir }}/team.toml. - Session Transcripts & Notes: Check local session memory indices or recent
.mdnotes for recurring friction points or debugging workarounds. - Recent Commits: Inspect recent commit messages and diffs for changes touching agent instructions, hooks, CI gates, or operational scripts.
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.
- yesterday First seen · 131 lines · 83 tokens per session scan A 2caabf3f88c7
upstream is a skill published in the GitHub repository NexaDuo/mARC (6 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,298 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 2026-09-09.
Other skills, from other repositories
quick-wrap
Short session close: commit, handle loose ends, stop. Not workstream-complete.
merging-to-main
Keyword-gated by name. Merges a ready branch to main: PR, CI, cleanup.
consolidate-git
Cleans up branch sprawl — consolidates and prunes stale branches.
finishing-a-development-branch
Presents merge, PR, or cleanup options once tests pass.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
pr-feedback
Work a reviewer's comments on a pull request to the end - all three comment surfaces enumerated before any is triaged, every comment fixed, declined with a reason, or ticketed, push before you reply. Use when a PR comes back with review feedback or a red check.