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 skills add backspace-shmackspace/claude-devkit --skill input-validation-injectiongit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWrote 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/backspace-shmackspace/claude-devkit/input-validation-injection)<a href="https://agentmods.dev/skills/backspace-shmackspace/claude-devkit/input-validation-injection"><img src="https://agentmods.dev/badge/skills/backspace-shmackspace/claude-devkit/input-validation-injection/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/backspace-shmackspace/claude-devkit/input-validation-injection"><img src="https://agentmods.dev/badge/skills/backspace-shmackspace/claude-devkit/input-validation-injection.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 | $0.00047 | $0.01055 |
| Opus 5.5 | $0.00019 | $0.00422 |
| Sonnet 5.5 | $0.00009 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
input-validation-injection 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 1mo 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.
This is a copy
92% identical to input-validation-injection — 16 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Input Validation and Injection Defense
Ensure untrusted input is validated and never interpreted as code. Prevent injection across SQL, LDAP, OS commands, templating, and JavaScript runtime object graphs.
Core Strategy
- Validate early at trust boundaries with positive (allow-list) validation and canonicalization.
- Treat all untrusted input as data, never as code. Use safe APIs that separate code from data.
- Parameterize queries/commands; escape only as last resort and context-specific.
Validation Playbook
- Syntactic validation: enforce format, type, ranges, and lengths for each field.
- Semantic validation: enforce business rules (e.g., start <= end date, enum allow-lists).
- Normalization: canonicalize encodings before validation; validate complete strings (regex anchors
^$); beware ReDoS. - Free-form text: define character class allow-lists; normalize Unicode; set length bounds.
- Files: validate by content type (magic), size caps, and safe extensions; server-generate filenames; scan; store outside web root.
SQL Injection Prevention
- Use prepared statements and parameterized queries for 100% of data access.
- Use bind variables for any dynamic SQL within stored procedures -- never concatenate user input into SQL.
- Prefer least-privilege DB users and views; never grant admin to app accounts.
- Escaping is fragile and discouraged; parameterization is the primary defense.
Example (Java PreparedStatement):
String custname = request.getParameter("customerName");
String query = "SELECT account_balance FROM user_data WHERE user_name = ? ";
PreparedStatement pstmt = connection.prepareStatement(query);
pstmt.setString(1, custname);
ResultSet results = pstmt.executeQuery();
LDAP Injection Prevention
- Always apply context-appropriate escaping:
- DN escaping for
\ # + < > , ; " =and leading/trailing spaces - Filter escaping for
* ( ) \ NUL
- DN escaping for
- Validate inputs with allow-lists before constructing queries; use libraries that provide DN/filter encoders.
- Use least-privilege LDAP connections with bind authentication; avoid anonymous binds for application queries.
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.
- 1mo ago First seen · 98 lines · 47 tokens per session scan A 9a05c04d5cb7
input-validation-injection is a skill published in the GitHub repository backspace-shmackspace/claude-devkit (15 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,055 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to input-validation-injection, differing in 16 lines, and is treated as a copy.
Other skills, from other repositories
architect
Produces Alon's design-doc system before code: SOURCEOFTRUTH.md, ARCHITECTUREROADMAP.md, TODOWORKFLOW.md, CLAUDE.md, plus a modular docs/architecture set for larger projects. Model first: data and invariants before framework, every invariant enforced at two boundaries, failure paths designed as deliberately as happy…
ponytail
Forces the laziest solution that actually works: YAGNI, reuse before new code, stdlib before custom, native platform before dependencies, one line before fifty. Three levels — lite (name the lazier alternative, build what's asked), full (ladder enforced, default), ultra (YAGNI extremist, challenge the requirement…
review-swarm
Local, free, multi-specialist review of a diff: parallel Claude subagents for correctness, security/trust boundaries, data/perf, architecture-altitude, ponytail-simplicity, and tests/failure-paths, each non-trivial finding adversarially verified before being kept, deduped, and ranked into a Blockers / Should-fix /…
ask-the-council
Convenes a panel of opinionated Claude advisors, each with a distinct mandate and a forbidden move so they genuinely diverge, then a Chairman synthesis that commits to one recommendation with the decisive tradeoff and the strongest dissent named.
prompt-generator
Turns a vague ask into a rigorous, grounded, token-efficient prompt for another agent or LLM: role and objective, testable done criteria, anti-hallucination and anti-tokenmaxing rules baked into the generated prompt itself, and strict agent discipline for coding-agent hand-offs.
up-to-date
Preflight sync and situational brief before repo work: fetches origin, reports ahead/behind divergence (with a no-upstream/detached-HEAD fallback), recent commits, open PRs and issues touching the work, and dirty-tree warnings, then names one recommended first action. Read-only by default — never pulls, rebases…