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/backspace-shmackspace/claude-devkit/input-validation-injectionnpx skills add backspace-shmackspace/claude-devkit --skill input-validation-injectiongit clone --depth 1 https://github.com/backspace-shmackspace/claude-devkitWhat 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 | $0.00047 | $0.01055 |
| Opus 5 | $0.00023 | $0.00528 |
| Sonnet 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 3d 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.
- 3d 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 9d ago), licensed MIT. It adds 47 tokens to every session and 1,055 once invoked, about $0.0002 per session on Opus 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
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
worktree-switching
Git worktree support in sidecar: worktree detection, switching between worktrees, worktree state management, and plugin reinitialization. Covers the full lifecycle of worktree context switching including registry reinit, per-worktree state persistence, deleted worktree detection and fallback. Use when working on git…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
ap-fresh-verifier
L4 blind fresh verifier - independently checks a candidate roadmap or plan against the exact mission and repository; APPROVE/REJECT, default-FAIL.
cron
Schedule reminders and recurring tasks.
agenticx-query-data-source
Use when the user asks about verifiable quantitative facts (stock prices, financial indicators, macro data, company registry, academic metrics, legal statutes) that must come from a live data source rather than training memory.