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/samibs/skillfoundry/_audit-exportgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/samibs/skillfoundry/_audit-export)<a href="https://agentmods.dev/agents/samibs/skillfoundry/_audit-export"><img src="https://agentmods.dev/badge/agents/samibs/skillfoundry/_audit-export.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.01367 |
| Opus 5 | $0.00000 | $0.00683 |
| Sonnet 5 | $0.00000 | $0.00273 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
_audit-export scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$WEBHOOK_URL" \ How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit Export Protocol
CORE FRAMEWORK MODULE Writes structured audit entries after each feature commit and gate decision. Entries are append-only. Optional webhook exports to external systems. Referenced by:
feature-lifecycle(Stage 5),forge(Phase 6),gate-keeper,hotfix
Purpose
Override logs in logs/overrides.md and evaluator verdicts in commit bodies live inside
the git repo and can be destroyed by force-push, branch deletion, or repo migration.
This protocol writes a parallel logs/audit-trail.jsonl (newline-delimited JSON, append-only)
and optionally POSTs entries to a webhook for external durability.
Entry Types
feature_commit
Written by feature-lifecycle at Stage 5 completion:
{
"ts": "ISO8601",
"type": "feature_commit",
"story_id": "STORY-001",
"feature": "JWT login flow",
"commit_hash": "abc1234",
"commit_message": "feat(auth): JWT login flow [STORY-001]",
"execution_mode": "REAL",
"stages": {
"implement": "done",
"testloop": {"status": "done", "iterations": 2, "tests_passed": 89, "tests_failed": 0, "coverage_lines": 91.2},
"semgrep": {"status": "done", "hard_blocks": 0, "warnings": 1},
"challenge": {"status": "done", "cycles": 2, "final_verdict": "✅"},
"document": "done",
"commit": "done"
},
"overrides_used": 0,
"files_committed": 7,
"complexity_tier": "MEDIUM"
}
override_decision
Written by any agent when --override is used:
{
"ts": "ISO8601",
"type": "override_decision",
"stage": "testloop",
"reason": "accepting 1 flaky E2E test — tracked in STORY-045",
"commit_context": "abc1234",
"user": "git-config-user-name",
"verdict_at_override": "🔴"
}
gate_blocked
Written by gate-keeper when a gate is locked (even if later resolved):
{
"ts": "ISO8601",
"type": "gate_blocked",
"stage": "STORY-001",
"violations": ["Missing unit tests in auth.service.ts", "Security headers not configured"],
"resolution": "auto-fixed | manually-fixed | overridden | unresolved",
"resolved_at": "ISO8601"
}
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 · 189 lines · 0 tokens per session scan A 8a1539e05660
_audit-export is an agent published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,367 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
Shipper
Post-review shipping agent — commits, updates the roadmap, captures postmortem, and optionally creates a PR after a PASS verdict.
Specifier
Interview the user to define what and why before any technical planning. Surfaces ambiguities as [NEEDS CLARIFICATION] markers that block hardening.
Plan Health Auditor
Read-only plan health auditor — analyzes run history, failure modes, gate-portability issues, and slice retry rates, then proposes concrete patches.
Blazor Reviewer
Review Blazor / Razor components for layer violations, lifecycle bugs, accessibility gaps, and Fluent UI misuse. Use for PR reviews on .razor / .razor.cs files.
Observability Reviewer
Audit code for observability gaps: structured logging, distributed tracing, metrics, health checks, and alerting readiness.
Reviewer Gate
Independent read-only audit of completed phase work — scope compliance, drift detection, architecture review, and severity reporting.