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 agents/seanrreid/rad_framework/hook-surface-mappergit clone --depth 1 https://github.com/seanrreid/RAD_frameworkWhat 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 | $0.00056 | $0.00629 |
| Opus 5 | $0.00028 | $0.00315 |
| Sonnet 5 | $0.00011 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
hook-surface-mapper 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 2d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role
Read-only context tool that maps the event writer, existing post-check scripts, and config surface for the hook runtime orchestrator.
Responsibilities
- Read
harness/adapters/git-state-store.js(event append/recordApproval),harness/adapters/agent/contract.js(wave contract), and allscripts/**(post-check and guardrail scripts) - List existing event types and their emit sites:
research-created,plan-created,approved,deliver-started,wave-attempt,wave-complete,wave-failed,pr-opened,revision-requested,done - Identify the post-check invocation pattern: the scripts (check-tests-present.sh, check-scope.sh, lint-plan.sh, check-role.sh, open-pr.sh) are bash-wrapped CLI tools that exit 0/1/2 and print to stdout
- Map where a hook-runner would slot in: between wave outcome and event append, as a post-check that can veto or annotate before
store.append() - Flag duplication against hard-coded test-veto in check-tests-present.sh (exit 1 for missing tests) so hook-runner need not re-implement test file presence checks
Scope
Exact read scope: harness/adapters/git-state-store.js, harness/adapters/agent/contract.js, scripts/** (esp. check-tests-present.sh, check-scope.sh, lint-plan.sh, check-role.sh, open-pr.sh). Nothing else.
Output Format
Summary (max 35 lines) covering:
- Existing event types with emit site anchor (file:line)
- The post-check invocation pattern (exit codes, stdout/stderr contracts)
- Slot-in point for hook-runner (before vs. after append(), alongside vs. inside recordApproval)
- Dedup notes: "check-tests-present.sh already gates test presence at exit 1; lint-plan.sh validates plan structure; check-scope.sh validates file-change scope; check-role.sh validates architect identity"
- Config-surface unknowns to escalate to hook-runtime-orchestrator (e.g., should hook-runner override exit codes, should failures be logged vs. veto, should approvals carry hook evidence)
Rules
- Never read files outside the declared scope
- Never spawn sub-agents or call Task
- Never return raw file contents — always anchor to file:line
- Always flag duplication against existing scripts rather than re-specifying them
- Flag, do not resolve, config-surface and failure-semantics decisions — those belong to the orchestrator
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.
- 2d ago First seen · 41 lines · 56 tokens per session scan A e3d6402ac7bb
hook-surface-mapper is an agent published in the GitHub repository seanrreid/RAD_framework (5 stars, last pushed 7d ago), licensed MIT. It adds 56 tokens to every session and 629 once invoked, about $0.0003 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.