Borrowing it
Nothing to install: this file belongs to stainless-code/codemap. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/stainless-code/codemap/main/.agents/skills/verify-after-each-step/SKILL.mdgit clone --depth 1 https://github.com/stainless-code/codemapWrote 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/stainless-code/codemap/verify-after-each-step)<a href="https://agentmods.dev/skills/stainless-code/codemap/verify-after-each-step"><img src="https://agentmods.dev/badge/skills/stainless-code/codemap/verify-after-each-step/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/stainless-code/codemap/verify-after-each-step"><img src="https://agentmods.dev/badge/skills/stainless-code/codemap/verify-after-each-step.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 12 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 23 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 25 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 26 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 28 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 29 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Memory Poisoning · line 30 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 23 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 25 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 26 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 28 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 29 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 30 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00022 | $0.00824 |
| Opus 5.5 | $0.00009 | $0.00330 |
| Sonnet 5.5 | $0.00004 | $0.00165 |
| Haiku 4.5 | $0.00002 | $0.00082 |
Grade A, and why
verify-after-each-step 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.
How it starts
The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify after each step (full checklist)
Always-on priming: .agents/rules/verify-after-each-step.md.
Run matching checks on every file touched before moving to the next milestone. Pre-commit is the safety net, not the first line of defense.
Discover project scripts
- Read
package.jsonscriptsat the start of a task. - Read
lint-staged.config.js— which checks apply to which patterns (staged-only tsgo, paired co-located tests). - Never assume script names — verify they exist in
package.jsonbefore running.
Per-file check table (this repo)
From lint-staged.config.js — mirror these between milestones, not only at commit:
| File pattern | Checks |
|---|---|
*.{js,jsx,ts,tsx,mjs,mts,cjs,cts} |
bun run format:check, bun run lint |
*.{css,json,md,mdc,html,yaml,yml} |
bun run format:check |
*.{ts,tsx} |
bun run typecheck with a temporary tsconfig.lint-staged.json that includes only staged files under src/ (project-wide types still interconnect — use bun run typecheck if you need full-project certainty); bun test on co-located *.test.{ts,tsx} pairs when a staged src/ source file is present but its test file is not |
*.test.ts |
bun test (on changed test files) |
*.test.tsx |
bun test (on changed test files) |
scripts/**/*.test.mjs |
bun test (on changed test files) |
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 · 53 lines · 22 tokens per session scan A b3152a1911cd
verify-after-each-step is a skill published in the GitHub repository stainless-code/codemap (8 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 824 once invoked, about $0.0001 per session on Opus 5.5. 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
roam
Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…
coograph-verify
Evidence-based completion check. Runs build, tests, and diagnostics itself and validates acceptance criteria, ending in a PASS / FAIL / INCOMPLETE verdict. Use when work is claimed complete.
test-driven-development
A test-driven development workflow, where a failing test is written before the implementation. Test-driven development, or TDD, is a way to build software by defining the expected behaviour in a test first.
verification-before-completion
Before claiming work is complete, run tea-rags imports/churn signals on just-edited files to surface collateral-damage candidates (files whose dependents could break), then run verification commands so success claims are backed by evidence and blast-radius awareness. Triggers on "ready to commit", "all done", "should…
tests-as-context
Five recipes turn DSL test chunks into review / verify / refactor / TDD enrichment. Owned by tea-rags, used by dinopowers wrappers and other tea-rags skills.
test-first
Agentic-only RED-phase skill — writes failing tests BEFORE implementation, from spec/plan acceptance criteria or given test code verbatim, else one test per behaviour of the task. Conventions from tests-as-context (fixture-lookup, assertion idioms of sibling tests). Runs them; each must fail for the RIGHT reason…