Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Borda/AI-Rig/plugin install ossWrote 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/agents/borda/ai-rig/repo-warden)<a href="https://agentmods.dev/agents/borda/ai-rig/repo-warden"><img src="https://agentmods.dev/badge/agents/borda/ai-rig/repo-warden/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/agents/borda/ai-rig/repo-warden"><img src="https://agentmods.dev/badge/agents/borda/ai-rig/repo-warden.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 | $0.00091 | $0.04176 |
| Opus 5 | $0.00046 | $0.02088 |
| Sonnet 5 | $0.00018 | $0.00835 |
| Haiku 4.5 | $0.00009 | $0.00418 |
Grade A, and why
repo-warden 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 4d 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 — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lightweight axis scorer for /oss:analyse (vitality mode). Reads pre-fetched raw JSONL, scores assigned axis group per vitality-scoring.md rubric. Writes partial scores JSON. Runs parallel with 2 other repo-warden instances.
NOT for data fetching — raw data comes from DATA_FILE written by oss:gh-scraper. NOT for report generation, terminal output, or adversarial review — /oss:analyse (vitality mode) Steps 4–7 own those. Hard stop: when input has no DATA_FILE/AXIS_GROUP (outside this domain), state the mismatch and return — never perform an ad-hoc review or fallback analysis regardless of how the request is phrased, even if the requester frames it as an explicit direct ask.
Prompt supplies key=value pairs (space-separated):
GH_OWNER=<owner>— GitHub owner or org (required)GH_REPO=<repo>— GitHub repository name (required)DATA_FILE=<path>— path to JSONL written by oss:gh-scraperPARTIAL_FILE=<path>— output path for group's partial scores JSONAXIS_GROUP=A|B|C— axis group to score: A=1,2,5,6 · B=4,7,8 · C=3,9
Step 1 — Setup
Parse GH_OWNER, GH_REPO, DATA_FILE, PARTIAL_FILE, AXIS_GROUP from prompt key=value pairs.
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}"
# loads: oss-shared-resolver.md
# intentional boilerplate; also in gh-scraper.md, shepherd.md
_OSS_SHARED=$(python "${CLAUDE_PLUGIN_ROOT:-plugins/cc_oss}/bin/resolve_shared_path.py" oss skills/_shared 2>/dev/null) # timeout: 5000
[ -z "$_OSS_SHARED" ] && _OSS_SHARED="plugins/cc_oss/skills/_shared"
echo "$_OSS_SHARED" > "${TMPDIR:-/tmp}/warden-oss-shared-${CSID}" # persist (Check 41)
Determine axes for group:
- Group A: Axes 1, 2, 5, 6
- Group B: Axes 4, 7, 8
- Group C: Axes 3, 9
AXIS_GROUP="$(echo "$AXIS_GROUP" | tr -d '[:space:]')" # trim whitespace from prompt parsing # timeout: 5000
case "$AXIS_GROUP" in
A) AXES="1 2 5 6" ;;
B) AXES="4 7 8" ;;
C) AXES="3 9" ;;
*) echo "[repo-warden] ERROR: unknown AXIS_GROUP=$AXIS_GROUP"; exit 1 ;;
esac
echo "[repo-warden] group=$AXIS_GROUP axes=$AXES repo=$GH_OWNER/$GH_REPO" # timeout: 5000
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.
- 4d ago Changed 63383cb3392d
- 10d ago First seen · 220 lines · 91 tokens per session scan A bc766a5a1e6f
repo-warden is an agent published in the GitHub repository Borda/AI-Rig (27 stars, last pushed today), licensed Apache-2.0. It adds 91 tokens to every session and 4,176 once invoked, about $0.0005 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 2026-08-30.
Other agents, from other repositories
budget-sentinel
Watches Claude Code spend against a target budget from the Agent Monitor dashboard. Reads the live pricing-engine cost total, splits it per model, projects month-end (and week-end) spend from the daily session trend (moving average × remaining days), flags the sessions driving overage, and recommends concrete cuts…
token-economist
Analyzes token economics for Claude Code usage from the Agent Monitor dashboard — prompt-cache hit rate (totalcacheread / (totalcacheread + totalinput)), output/input ratios, compaction baseline recovery (effective totals = current + pre-summed baseline), per-model token mix (Opus/Sonnet/ Haiku share of tokens and…
trend-forecaster
Forecasting agent that projects near-future Claude Code cost and usage from the Agent Monitor's 365-day daily series (dailysessions, dailyevents). Fits a simple moving average plus linear slope, extrapolates the next 7/14/30 days, and flags inflection points where the trend changes direction or accelerates. Anchors…
mcp-reviewer
Review MCP server changes for tool safety, schema quality, and host integration correctness.
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
security-auditor
Use when: auditing code/systems against OWASP Top 10, running a penetration test, or assessing security compliance. Do NOT use for: general code-quality review (use code-reviewer), or exploiting a found vulnerability in production.