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 Ancienttwo/repo-harness --skill auto-campaigngit clone --depth 1 https://github.com/Ancienttwo/repo-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/ancienttwo/repo-harness/auto-campaign)<a href="https://agentmods.dev/skills/ancienttwo/repo-harness/auto-campaign"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/auto-campaign/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/ancienttwo/repo-harness/auto-campaign"><img src="https://agentmods.dev/badge/skills/ancienttwo/repo-harness/auto-campaign.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 | $0.00068 | $0.00892 |
| Opus 5 | $0.00034 | $0.00446 |
| Sonnet 5 | $0.00014 | $0.00178 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
auto-campaign 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 today.
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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto-campaign
One user invocation authorizes one conversational campaign turn, not one model API call. Coordinate the existing CLI until a stop boundary, then report and return control. No daemon, cron, hook-triggered execution, automatic next turn, or automatic merge.
Start from the current repository
- Resolve the target repository, target ref, current host/session and any campaign ID from the request and existing session. Ask only for missing consequential inputs. Do not infer an unrelated repository or resume the most recent campaign merely because it exists.
- Read execution.md for authoritative input sources, CLI steps and recovery. Inspect policy at the exact target revision, external-source selection, browser binding and permitted worker environment before any grant or provider effect. An off policy, unavailable capability, unresolved reservation, or prohibited execution base ends this invocation as blocked. Report the concrete prerequisite; do not change policy, install infrastructure or start a trial provider call to make preflight pass.
- Read standard.json, the sole source of default limits. Render its scope and bounds in plain language. Token and monetary caps are null: do not claim a hard token or cost budget. An explicit different budget is a separately reviewed grant, not a silently modified standard.
New turn or continuation
- New: prepare the canonical draft with
scripts/prepare-grant.ts. Show the target, Issue scope, execution environment, grant expiry and concrete limits. Reuse explicit approval already covering these values; otherwise obtain it before minting or provider calls. Invocation is not permission to invent the issuer, broaden scope, or enable a disabled feature. The helper only emits a draft; the existing grant store and campaign commands own all mutations. - Resume: read the exact original campaign, grant, intent, worktree ownership and budget ledger first. Preserve IDs, idempotency keys and remaining budget. Do not run the draft helper again, extend expiry, replace the grant, reset counters or revive a stopped campaign. If a new grant or recovery decision is required, stop and explain it. Context compaction does not start a new turn.
What ships with it
3 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.
- today First seen · 76 lines · 68 tokens per session scan A b02adf6ad99e
auto-campaign is a skill published in the GitHub repository Ancienttwo/repo-harness (431 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 892 once invoked, about $0.0003 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 2026-09-10.
Other skills, from other repositories
aidex-bugfix
Use when fixing a bug, resolving a reported issue, or when something is broken and needs a test-driven fix — investigate root cause, write a failing regression test (RED), implement the minimum fix, confirm the test passes (GREEN), then commit test and fix together. Fires on "fix this bug", "this is broken", "it's not…
bug-fixing
Fix defects in the Composio SDK repository with focused reproduction, root-cause analysis, regression tests, and narrow verification. Use when the user reports a bug, failing test, CI regression, runtime defect, or incorrect SDK behavior. Do not use for new feature design or broad refactors.
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
python-testing
Select and run Python SDK verification with nox, Makefile targets, Ruff, mypy, pytest markers, sanity tests, type inference checks, and build checks. Use when adding Python tests, diagnosing Python CI, or validating Python SDK/provider changes. Do not use for TypeScript-only checks.
typescript-testing
Select and run TypeScript SDK verification for packages, examples, type checks, linting, builds, Vitest suites, and runtime E2E tests. Use when adding tests, diagnosing TypeScript CI, choosing a focused test command, or validating TypeScript package changes. Do not use for Python-only checks.
potpie-debug-memory
Use while debugging or troubleshooting failures, flaky tests, incidents, production alerts, CI failures, local dev setup issues, repeated bugs, prior fixes, failed attempts, and verification history.