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 agentmods add agents/hannsxpeter/godpowers/securitygit clone --depth 1 https://github.com/hannsxpeter/godpowersWhat 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 | $0.00000 | $0.01264 |
| Opus 5 | $0.00000 | $0.00632 |
| Sonnet 5 | $0.00000 | $0.00253 |
| Haiku 4.5 | $0.00000 | $0.00126 |
Grade A, and why
security 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope
- [DECISION] This pillar captures security boundaries for Godpowers runtime and release work.
Context
- [DECISION] Installer, bridge, shell-execution, dependency, and publication surfaces receive adversarial review before release.
Decisions
- [DECISION]
lib/evidence.resolveReviewEvidenceis a read-only local resolver that checks one exact record against expected claim, command, canonical substep, freshness, digest-bound gate event, and event hash chain. - [DECISION] Stage 2 receives the resolver's sanitized projection without raw ledger records, event attributes, commands, claims, stdout tails, or stderr tails.
- [DECISION] The resolver proves internal consistency only inside a trusted workspace; it does not authenticate against an actor able to rewrite every trusted file and recompute the chain.
- [DECISION] The 6.2.0 prepublication gate passed at
2026-08-19T10:07:48.020Zagainst hardening revisionsha256:5f65a4de4bb0ab7dcce5e7fb11c182a77345f23b2e6f75077c549ccef4ce9268with zero Critical findings. - [DECISION] The isolated exact 6.2.0 package pair reported zero vulnerabilities, and
npm audit signaturesverified registry signatures and attestations for all 5 installed packages. - [DECISION] The 6.3.0 decision writer and reader share one bounded allowlisted validator that rejects credential fields, common provider tokens, URL userinfo, all query strings, and unsafe fragments before append or projection.
- [DECISION] The 6.3.0 route loader derives command authority from canonical filenames and rejects duplicate, spoofed, or noncanonical route YAML.
- [DECISION] Unknown route prerequisite predicates fail closed, and every named non-prefixed predicate used by a canonical route has explicit bounded behavior.
- [DECISION] Event readers reject traversal and linked run paths, and event snapshots fail closed above 8 MiB or 50,000 lines.
- [DECISION] SkillUI validates remote targets but never passes URLs or remote repository locations to the external CLI; remote forms require an already reviewed local directory.
- [DECISION] Runtime verification profiles and debug feedback records cap collections and recursive validation before generating result objects.
- [DECISION] Manual pack workflow inputs cross through environment variables, then pass a pack allowlist and strict SemVer validation before shell use.
- [DECISION] Root and MCP recovery publication requires registry integrity and shasum to match the exact packed candidates before promotion.
- [DECISION] The final 6.3.0 harden gate passed with one executed-backed release command, and the fresh prepublication gate passed against hardening revision
sha256:69bd088dc44e405b144536bd51701088bb0da7d5e2200685e9b3e13be7403f5fwith zero unresolved or accepted Critical findings. - [DECISION] The optional operations-pack setup template keeps secrets off command arguments, rejects tracked environment destinations, verifies exact repository authority, and uses temporary replacement with cleanup and error propagation.
- [DECISION] The exact published 6.3.0 root, MCP, and operations-pack install reported zero vulnerabilities, and
npm audit signaturesverified registry signatures and attestations for all 6 installed packages.
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 · 79 lines · 0 tokens per session scan A a5bf64244efe
security is an agent published in the GitHub repository hannsxpeter/godpowers (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,264 tokens. 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
ap-framework-generator
L3 executor - FRAMEWORK GENERATE. When the SELECTOR returns MISS, generates a one-off custom framework for the exact task shape - classifies the orthogonal axes, composes the gate sequence from the GATE-LIBRARY with the correct axis-specific gate, emits the gen- leaf with the BLOCKED invariant verbatim, binds an…
ap-juror
L4 terminal leaf - G7 SIGN-OFF. One independent sign-off panel seat that saw none of the intermediate work. Binary PASS/FAIL on opened evidence; default-FAIL. A FAIL naming a P0/P1 blocker is NOT arbitrable into PASS.
ap-verifier
L3 independent G6 verifier - proves behavior with real before/after runs, regression checks, adversarial inputs, and >=95% changed-line coverage.
ap-re-anchor
L4 terminal leaf - RE-ANCHOR. Confirms mission and roadmap frontier alignment after resume or compaction using the three-file governance state.
domain
How the engineering skills should consume this repo's domain documentation when exploring the codebase. This is a single-context repo.
ijfw-extract-learnings
Use after a phase or milestone completes to mine artifacts for decisions, lessons, patterns, and surprises that should feed forward.