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 RudraDudhat2509/claude-skills --skill oss-copilotgit clone --depth 1 https://github.com/RudraDudhat2509/claude-skillsWrote 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/rudradudhat2509/claude-skills/oss-copilot)<a href="https://agentmods.dev/skills/rudradudhat2509/claude-skills/oss-copilot"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/oss-copilot/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/rudradudhat2509/claude-skills/oss-copilot"><img src="https://agentmods.dev/badge/skills/rudradudhat2509/claude-skills/oss-copilot.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 | $0.00119 | $0.01314 |
| Opus 5 | $0.00060 | $0.00657 |
| Sonnet 5 | $0.00024 | $0.00263 |
| Haiku 4.5 | $0.00012 | $0.00131 |
Grade A, and why
oss-copilot 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 11d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OSS Co-Pilot
Rudra's end-to-end OSS contribution assistant. Primary niche: LLM security — agentic attack surfaces (MCP tool poisoning, agent memory poisoning, multi-agent attack chains). Expanded scope: any repo that builds job-readiness for target companies (Portkey.ai, Langfuse, Arize AI, Palantir, Scale AI) — including LLM observability, eval frameworks, agent orchestration, production AI infrastructure, and agentic backend tooling. Target: build a visible, technically credible OSS track record before graduation (2028).
Workflow
Three phases, always in this order:
Phase 1 → Discover — Search GitHub for the single best issue to work on right now.
Phase 2 → Pick — Present one recommendation with full context. Rudra confirms or asks for another.
Phase 3 → Execute — Full session: orient → env check → explain codebase → build → pre-PR checklist → post-push.
At session end: auto-update oss/CLAUDE.md status table + append to session_log.md.
Phase 1: Discover
Search GitHub fresh every session — do NOT rely on the tracked repo list in oss/CLAUDE.md.
Run multiple gh search issues queries in parallel — see references/issue-search.md for the full query list and high-value repo table.
Quick pre-filter (drop anything that fails these before spawning agents):
- Issue is open
- Repo has been active in the last 6 months
- Not labeled
closed,duplicate,wontfix
For every candidate that passes the pre-filter, spawn one Issue Verification Agent per candidate (run in parallel). Each agent does a 4-layer check:
- Layer 1: assignee + labels
- Layer 2: full comment scan for claiming language, code snippets, bot assignments
- Layer 3: linked PRs (open + merged) + GitHub timeline cross-references
- Layer 4: commit history scan + spot-check if the feature/fix already exists in the codebase
The agent returns: VERDICT: CLEAR / CLAIMED / UNCERTAIN with a one-line reason.
Full agent prompt and all gh commands are in references/issue-search.md → Issue Verification Agent.
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.
- 11d ago First seen · 113 lines · 119 tokens per session scan A 7768bf976886
oss-copilot is a skill published in the GitHub repository RudraDudhat2509/claude-skills (2 stars, last pushed 18d ago), licensed MIT. It adds 119 tokens to every session and 1,314 once invoked, about $0.0006 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
atmos-vendoring
Component vendoring: vendor.yaml and component.yaml manifests, immutable vendor.lock.yaml receipts, pulling from Git/S3/HTTP/OCI/Terraform Registry, --stack/--labels/--tags selector composition, native vendor update, clean, diff, config, and reviewed local component copies.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims, signed commits, managed workdirs, fork-PR trust gate, and auth via identities or github/sts.
git-revert-safety
Apply when reverting commits, undoing merges, or recovering from branch contamination. Covers collateral damage verification (manifest, package.json, CHANGELOG, lockfiles), cherry-pick vs revert decision matrix, partial-revert detection, merge-parent handling, and post-revert CI verification. Prevents the most common…
safe-extraction
Apply when extracting code from a large monolith file into submodules. Covers barrel re-exports, internals DI seam proxy patterns, CI invariant allowlist updates, and cross-file test verification. Prevents CI failures, broken imports, and test regressions from code extraction.