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/edenfunf/promptc/legacy-rulesnpx skills add edenfunf/promptc --skill legacy-rulesgit clone --depth 1 https://github.com/edenfunf/promptcWrote 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/edenfunf/promptc/legacy-rules)<a href="https://agentmods.dev/skills/edenfunf/promptc/legacy-rules"><img src="https://agentmods.dev/badge/skills/edenfunf/promptc/legacy-rules.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 5.1 | $0.00003 | $0.00240 |
| Opus 5 | $0.00002 | $0.00120 |
| Sonnet 5 | $0.00001 | $0.00048 |
| Haiku 4.5 | $0.00000 | $0.00024 |
Grade A, and why
legacy-rules 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 6d 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
Legacy rules
Older guidance the team accumulated before consolidating onto the current toolchain. Some of these are still in force; some have been superseded by newer skills but the file was never cleaned up.
Linting
Run pylint before every commit; CI rejects PRs with new pylint
warnings. (This is partly stale — most teams have moved to ruff,
but a couple of services still run pylint locally because their
configurations were never migrated.)
SQL access
Always use parameterized queries for every database access. Never concatenate user-provided strings into SQL statements directly. This includes dynamic WHERE clauses, ORDER BY clauses, and table names.
Type hints
Type hints are now required across the codebase (see python-style).
This file predates that decision; treat the older "type hints are
optional" guidance some skills carry as superseded.
Boundary discipline
Treat any data that crossed a network or process boundary as untrusted until proven otherwise. Apply the same scrutiny to data from other internal services as you would to data from the public internet.
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.
- 6d ago First seen · 35 lines · 3 tokens per session scan A 29a11dff1a52
legacy-rules is a skill published in the GitHub repository edenfunf/promptc (2 stars, last pushed 4mo ago), licensed MIT. It adds 3 tokens to every session and 240 once invoked, about $0.0000 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
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
grill-me
Two modes, picked from the file you point it at. Contract mode grills a claude-contract.md line by line until every line is a thing Claude must always do or must never do, editing that file in place and creating nothing new. Brief mode interrogates a design brief until it has no soft spots left, then produces a…
information-architecture
Map the user journey first, then derive the screen inventory, navigation and hierarchy from it, flagging any screen that serves no journey step. Writes the four-part markdown plus an HTML diagram of the step-to-screen mapping. Use after the brief is settled and before tokens or UI.
design-tokens
Establish color, typography, spacing, radius and motion as named role-based tokens. Use before building any interface.
heuristic-evaluation
Audit a design against Nielsen's ten usability heuristics, tying every finding to a specific element with a specific fix. Use on a built screen or a detailed mockup.
persona-acid-test
Stress-test a design through three lenses, confused user, skeptical engineer and impatient PM, before it goes to a stakeholder. Requires an actual design, an HTML file, Figma link or screenshot.