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 akashsebastian333/peephole/plugin install peepholeWrote 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/akashsebastian333/peephole/sec-debt)<a href="https://agentmods.dev/skills/akashsebastian333/peephole/sec-debt"><img src="https://agentmods.dev/badge/skills/akashsebastian333/peephole/sec-debt/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/akashsebastian333/peephole/sec-debt"><img src="https://agentmods.dev/badge/skills/akashsebastian333/peephole/sec-debt.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 | $0.00053 | $0.00432 |
| Opus 5 | $0.00026 | $0.00216 |
| Sonnet 5 | $0.00011 | $0.00086 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
sec-debt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Peephole sec-debt
A sec-debt marker is how a deliberate security trade-off is recorded so it is auditable instead of silent. Write it as a comment on or directly above the flagged line — a marker only applies to findings near it, never to the whole file:
# sec-debt: CWE-89 — internal admin tool, network-isolated; upgrade path: parameterize before exposing
Rules (binding):
- A marker is a request, not a grant. The agent cannot self-authorize. In strict mode a marker converts a would-be deny into an ask — a human decides. In hardened mode the deny stands (a hook cannot collect the typed confirmation); the human lowers to strict/audit to accept the trade-off.
- Every waiver is audit-logged. A marker without a matching human approval is
treated as an evasion attempt: flagged at Stop and in
/sec-audit, never silently honored. - The stated precondition is the contract. If it stops holding (e.g. the route becomes public), the debt should be revisited.
To list outstanding sec-debt
Run:
sh "$CLAUDE_PLUGIN_ROOT/hooks/peephole.sh" debt
It scans the codebase for every sec-debt: marker and cross-checks each against
.peephole/secdebt-approved, flagging any UNAPPROVED marker as an evasion
risk. A human approves a marker by adding its file (or file:line) to
.peephole/secdebt-approved. Review each unapproved marker: confirm the stated
precondition still holds, or fix the underlying issue.
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.
- 11d ago First seen · 41 lines · 53 tokens per session scan A 9d9a6140f815
sec-debt is a skill published in the GitHub repository akashsebastian333/peephole (5 stars, last pushed 12d ago), licensed MIT. It adds 53 tokens to every session and 432 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 2026-08-31.
Other skills, from other repositories
assessing-vector-and-embedding-weaknesses
Test vector stores for embedding inversion, cross-tenant leakage, and poisoning.
detecting-data-and-model-poisoning
Identify poisoned training data and backdoored models across the ML pipeline.
detecting-model-extraction-attacks
Detect model stealing, model inversion, and membership inference performed through inference-API abuse by monitoring query patterns, applying output perturbation, and red-teaming your own model's extractability.
orchestrating-llm-attacks-with-pyrit
Build multi-turn, Crescendo, and Tree-of-Attacks-with-Pruning (TAP) automated attack chains against conversational LLM agents using Microsoft PyRIT, with adversarial chat and scorer feedback loops.
securing-agentic-ai-tool-invocation
Apply least-privilege tool allowlisting, identity binding, and human-in-the-loop controls for agent tool calls.
continuous-llm-red-teaming-with-promptfoo
Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.