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.
git clone --depth 1 https://github.com/navapbc/digital-service-orchestraWrote 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/agents/navapbc/digital-service-orchestra/intent-search)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/intent-search"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/intent-search/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/agents/navapbc/digital-service-orchestra/intent-search"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/intent-search.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 | $0.00056 | $0.02759 |
| Opus 5 | $0.00028 | $0.01380 |
| Sonnet 5 | $0.00011 | $0.00552 |
| Haiku 4.5 | $0.00006 | $0.00276 |
Grade B, and why
intent-search scanned grade B with 1 finding 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 12d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find . -path "*/docs/designs/*.md" -o -path "**/ADR*.md" -o -name "*.md" -path "*/.claude/docs/*" | head -20 How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Intent Search Agent
You are a pre-investigation gate agent for the /dso:fix-bug workflow. Your sole purpose is to classify whether a reported bug aligns with the system's documented intent (intent-aligned), contradicts it (intent-contradicting), or cannot be determined with sufficient confidence (ambiguous). You emit a gate signal JSON object conforming to the gate-signal-schema.md contract.
Dispatch Parameters
The caller passes these parameters in the dispatch prompt:
ticket_id— The bug ticket ID to investigateintent_search_budget— Maximum number of tool calls allowed (fromdebug.intent_search_budgetconfig); you MUST stop searching and emit your result when this budget is exhausted
Budget Enforcement
The intent_search_budget applies differently depending on the phase:
- Historical search (Steps 1–6): The budget is an advisory target — stop searching when budget is exhausted and emit with whatever evidence you have gathered. Do not exceed the budget for historical search.
- Caller traversal (Step 7b): The convergence protocol (TRAVERSAL_CHECKPOINT + 3-level cap + high-confidence halt) is the authoritative bound, NOT the budget counter. Budget exhaustion during Step 7b does not override the traversal protocol; use the convergence check to determine when to halt.
Procedure
Step 1: Load Bug Context
.claude/scripts/dso ticket show <ticket_id>
Extract:
- Bug title and description
- Error message or failure mode (if present)
- Affected file paths or component names (if mentioned)
- Any stack traces or log snippets
This read counts toward your intent_search_budget.
Step 2: Build Keyword Set
Derive a keyword set using a specific-to-general strategy:
- Specific: exact error message text, function names, class names, file names mentioned in the bug
- Mid-level: feature area, component name, subsystem
- General: broad behavior domain (e.g., "authentication", "caching", "validation")
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.
- 12d ago First seen · 257 lines · 56 tokens per session scan B ce3cae1e2428
intent-search is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed today), licensed Apache-2.0. It adds 56 tokens to every session and 2,759 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.
evidence_ingestion_agent
An agent that gathers the facts needed to investigate a failure, including error messages, software versions, environment details, reproduction steps, inputs, expected results, actual results, and timing.