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 skills/konstruktoid/prescryb/python-secure-codingnpx skills add konstruktoid/prescryb --skill python-secure-codinggit clone --depth 1 https://github.com/konstruktoid/prescrybWhat 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 | $0.00098 | $0.02317 |
| Opus 5 | $0.00049 | $0.01158 |
| Sonnet 5 | $0.00020 | $0.00463 |
| Haiku 4.5 | $0.00010 | $0.00232 |
Grade C, and why
python-secure-coding scanned grade C with 2 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Vendored from https://github.com/konstruktoid/agent-instructions-skills skills/python/python-secure-coding/SKILL.md Upstream commit: f4696ac18174422ba873bac1630628d49123c7c0 Do not edit locally; re-vendor from upstr Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
| `subprocess`, `os.system`, shell strings, `eval`/`exec` | [references/injection.md](references/injection.md) | The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
6 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.
- yesterday First seen · 170 lines · 98 tokens per session scan C 8a24a8627c06
python-secure-coding is a skill published in the GitHub repository konstruktoid/prescryb (1 stars, last pushed 5d ago), with no licence file. It adds 98 tokens to every session and 2,317 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
azure-security-audit
Azure NSG compliance auditing and security posture assessment. CIS Azure Foundations Benchmark rules, effective security rule analysis, orphaned NSG detection. Use when auditing Azure NSGs for CIS compliance, checking for overly permissive rules, or reviewing effective security on NICs.
hardening
Complete security hardening of a Linux server based on CIS Benchmarks, NIST 800-123, and ANSSI BP-028. Smart service discovery to avoid disruption. 4 hardening levels (minimal/standard/enhanced/paranoid). Installs open-source security tools, hardens SSH/kernel/firewall/systemd/permissions, runs all scans, generates a…
catalyst-center-readonly
Query Cisco Catalyst Center read-only — device inventory, site hierarchy, wireless, assurance health, compliance, software images, events. All 514 read-only API operations reachable through 8 grouped dispatchers. Use when asked what Catalyst Center manages, where a device sits, what its health or compliance state is…
aws-security-audit
AWS security auditing — IAM users/roles/policies, CloudTrail API events, security posture analysis. Use when auditing IAM permissions, investigating security incidents, checking MFA compliance, or tracing API activity in CloudTrail.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
bob-status
Read Hacker Bob session state, wave status, findings, verification, and grade summaries.