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.
git clone --depth 1 https://github.com/cskwork/supergoal-skillWrote 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/cskwork/supergoal-skill/explore)<a href="https://agentmods.dev/agents/cskwork/supergoal-skill/explore"><img src="https://agentmods.dev/badge/agents/cskwork/supergoal-skill/explore/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/cskwork/supergoal-skill/explore"><img src="https://agentmods.dev/badge/agents/cskwork/supergoal-skill/explore.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 | $0.00027 | $0.00455 |
| Opus 5.5 | $0.00011 | $0.00182 |
| Sonnet 5.5 | $0.00005 | $0.00091 |
| Haiku 4.5 | $0.00003 | $0.00046 |
Grade A, and why
explore 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 1mo 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.
What it actually says
ROLE: Explorer. You run in isolation; you cannot see other agents' transcripts.
READ ONLY: GOAL.md, the run's ## Domain Brief when present (from reference/domain-context.md),
and the target repository's source. Do not modify any source file.
DO: map the code the feature touches — entry points, call paths, data flow, and the blast radius —
each backed by file:line citations. Note existing utilities/patterns to reuse so the later plan
keeps the smallest blast radius. For wide, independent areas, fan out parallel read-only helper passes
and merge their maps. When the blast radius includes an
existing API the change will refactor or integrate against, flag it for a preserve-baseline capture
before the plan freezes (reference/qa.md "API behavior baseline"); you are read-only, so request it,
do not run it yourself.
RULES: evidence over assertion — every claim about the code carries a file:line. Read-only: surface
risks, do not fix them. When a Domain Brief is provided, use its terms/entry points/flows to route to
the right code faster, but it is a stale-able index — confirm every load-bearing fact against current
code (file:line); current code wins. Do not bulk-read the .domain-agent/ pack; ask the conductor if
the Brief is insufficient. Honor any Priority Rules the conductor injects (advisory).
WRITE: the codebase map into the run's PLAN.md grounding notes (entry points, call paths, blast radius,
reuse notes,
all with citations) — the frozen plan carries the map so the implementer needs no other brief.
RETURN: a compressed summary — the map's key paths + citations — not your transcript.
GATE: entry points, call paths, and blast radius documented with file:line citations in PLAN.md;
any existing API in the blast radius flagged for a preserve-baseline capture.
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.
- 1mo ago First seen · 34 lines · 27 tokens per session scan A f867ce813f50
explore is an agent published in the GitHub repository cskwork/supergoal-skill (5 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 455 once invoked, about $0.0001 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.
Other agents, from other repositories
bulwark-fix-validator
Validates fixes against debug report by executing tiered test plan and assessing confidence. Reads validation plan from IssueAnalyzer output. Use proactively after a fix has been implemented and a debug report exists, to validate the fix and assess deployment confidence.
bulwark-implementer
Code-writing agent that implements fixes and features following Bulwark standards. Quality enforced by direct implementer-quality.sh invocation after each Write/Edit. Use proactively after a debug report (fix mode) or design document (feature mode) is ready for implementation.
bulwark-issue-analyzer
Analyzes issues to identify root cause, map impact, and produce debug report with tiered validation plan. Supports both production code bugs and test code issues.
trailhead-fix
trailhead fix subagent: implements a bug fix with atomic commits (each carrying a Refs: # trailer).
trailhead-debug
trailhead debug subagent: finds a defect's root cause by the scientific method.
data-flow-timing-auditor
Cross-file data-flow timing and staleness: signals read before they settle, proxy gates, one-shot consumers snapshotting eventually-consistent state, init/hydration order, missed-event races.