---
schema_version: "newruntime-agent-readable-v0.2"
type: "project_acceptance_checklist"
stable_id: "project_acceptance_checklist:coding-agent-cost-controls"
project_slug: "coding-agent-cost-controls"
project_title: "Coding Agent Cost Controls"
buildability_class: "B2"
verification_status: "locally-reproduced"
proof_artifact_count: 6
buildability_axis_count: 7
replay_evidence_count: 2
project_status: "candidate"
last_verified: "2026-08-15"
record_date: "2026-08-15"
date_kind: "last_verified"
routes: {"build_brief":"https://newruntime.com/projects/coding-agent-cost-controls/build-brief.md","project_json":"https://newruntime.com/projects/coding-agent-cost-controls.json","html":"https://newruntime.com/projects/coding-agent-cost-controls/"}
---

# Acceptance checklist: Coding Agent Cost Controls

## Required checks

- A failing test still shows the failing file, assertion, command, and exit status.
- The agent can identify the intended files without reading the whole repository first.
- The cost-control change reduces irrelevant output without hiding actionable diagnostics.
- The handoff report includes before/after command evidence, changed files, and residual risk.

## Permission and cleanup contract

| Access | Purpose | Minimum scope | Confirmation | Cleanup |
| --- | --- | --- | --- | --- |
| read | Inspect repository structure and local command output. | Local repo files and generated logs for the selected task only. | Human names the repo and task before inspection. | Remove temporary measurement logs after recording the aggregate before/after numbers. |
| write | Edit local agent config or wrapper scripts. | Focused local files under the chosen repo; no deploy, commit, or push. | Human approves the exact files before edits are applied. | Revert the focused config/script change or restore the previous file version if diagnostics are hidden. |

## Reproducibility notes

- Save the exact before and after commands so another agent can rerun the comparison.
- Record both cost signal and correctness signal; lower tokens without passing checks is a failure.

## Fixture outputs

- Built project JSON: dist/projects/coding-agent-cost-controls.json (https://newruntime.com/projects/coding-agent-cost-controls.json). Check: The route contains proof, handoff, permissions, source URLs, and agent-readable routes for this project.
- Agent acceptance checklist: dist/projects/coding-agent-cost-controls/acceptance.md (https://newruntime.com/projects/coding-agent-cost-controls/acceptance.md). Check: The checklist repeats required checks, provider scopes, reproduction commands, and failure conditions.
- Build brief handoff: dist/projects/coding-agent-cost-controls/build-brief.md (https://newruntime.com/projects/coding-agent-cost-controls/build-brief.md). Check: The build brief can be handed to another agent without private context or hidden source dependencies.
- Clean-room replay fixture: scripts/project-proof-depth-v2-fixture-test.mjs. Check: The fixture replays the bounded log-trimming task in a temporary directory, proves that the initial implementation hides the failure and warning lines, proves the final pass, and verifies that an unrelated file is unchanged.
- Independent replay kit: scripts/project-proof-independent-replay-kit.mjs. Check: The kit starts with a trim function that hides failures, exposes no ready solution, protects every out-of-scope file by checksum, and refuses to emit a receipt without a non-author attestation and a passing final check.
- Independent agent replay receipt: src/data/project-proof-receipts/coding-agent-cost-controls-independent-agent-v1.json (https://newruntime.com/projects/coding-agent-cost-controls.json). Check: A separately spawned agent received only the isolated kit, observed the hidden-failure regression, changed only src/trim-log.mjs, passed the final check, and produced an attestation that the primary verifier accepted.

## Reproduction commands

1. npm run project-proof:replay:test
2. npm run project-proof:replay:prepare -- --project=coding-agent-cost-controls
3. npm run validate:content
4. npm run build
5. npm run validate:agent-indexes

## Expected artifacts

- A before/after measurement note with command, token or output-size signal, elapsed time, and pass/fail result.
- A focused repo-map or wrapper-script diff that trims noisy output without hiding actionable failures.
- A cleanup note for any temporary local logs used to measure the workflow.

## Buildability breakdown

| Axis | Level | Evidence | Bottleneck |
| --- | --- | --- | --- |
| time | high | The clean-room log-trimming task reaches a checked result in one bounded local run, while the public blueprint targets a half day for one narrow repository. | Real before/after cost measurement still needs repeated agent runs on the chosen repository. |
| code burden | medium | The replay needs one focused filter edit plus the existing test, and the public blueprint needs only repo maps, wrapper scripts, and config rather than a bespoke application. | A nontechnical owner still needs an agent or engineer to identify which output paths are noisy but safe to trim. |
| integration burden | medium | The replay uses only Node, a test runner, and one deterministic filter function with no external service. | Each target repository needs its own noisy-output inventory and repo-specific hooks before the controls transfer. |
| operational burden | high | The first proof is local and temporary, requires no server, and deletes no shared or production state. | Continuous cost monitoring across many repositories would need scheduled measurement and log-retention rules. |
| permission clarity | high | Read and local-write scopes are named separately, the Git remote scope is explicitly none for the first pass, and commit, push, and deploy stay behind a separate owner command. | Deploying trimmed-output wrappers into shared CI would reopen the approval question. |
| reproducibility | high | A separately spawned agent received only the isolated public kit, reproduced the initial check where the trim function hid the failure and warning lines, changed the one allowed filter file, and passed the same acceptance check without inspecting the author solution. | A replay on a real noisy repository with token measurements would strengthen the savings claim beyond this bounded fixture. |
| failure recovery | high | The replay records the initial failing check, preserves an unrelated file byte-for-byte, performs no remote action, and leaves explicit residual-risk and approval sections. | Restoring hidden diagnostics inside a production agent pipeline is outside this local proof. |

## Replay evidence

### clean-room-bounded-edit-v1

- Date: 2026-08-15.
- Kind: automated-clean-room.
- Outcome: passed.
- Command: npm run project-proof:replay:test.

- This replay proves the deterministic diagnostic-preserving output contract, not a real external repository integration or measured token savings.
- No human or separately operated agent independently interpreted the brief in this clean-room replay.

### independent-claude-replay-v1

- Date: 2026-08-15.
- Kind: independent-agent.
- Outcome: passed.
- Command: node --test test/trim-log.test.mjs.

- This proves a bounded non-author replay of the public workflow contract, not integration into a production repository.
- Reviewer identity is a local agent attestation and is not cryptographically verified.

## Provider scopes

| Provider | Access | Minimum scope | Why needed | Approval gate |
| --- | --- | --- | --- | --- |
| Local repository | write | Selected repo-map, wrapper-script, or agent-config files only. | The cost boundary is enforced by local configuration and deterministic command output shaping. | Human names the repository and approves the exact files before edits. |
| Git remote | none | No remote write access is required for the first proof pass. | The project proves local cost controls before any commit, push, or deploy. | Commit, push, or deploy require a separate explicit owner command. |

## Known limits

- This proof does not claim universal token savings; it requires a selected repository and repeated task type.
- A lower output volume is not success unless the same correctness checks still fail or pass with useful diagnostics.
- Provider-side billing dashboards are outside the public proof route and must remain private.
- The bounded replay proves the diagnostic-preserving output contract, not measured token savings on a real repository; savings claims still need a per-repository before/after measurement.
- The independent replay proves the bounded public workflow contract, not integration into a real external or production repository.
- The independent reviewer identity is a local agent attestation and is not cryptographically verified.

## Failure conditions

- The claimed output cannot be reproduced from the build brief and public/project-local inputs.
- The implementation needs broader permissions than the minimum scopes listed above.
- Private discovery provenance, secrets, raw exports, or unapproved write actions appear in a public artifact.
- The current bottleneck remains unresolved: Needs repo-specific hooks and enough measurement to avoid hiding useful diagnostics.

## Evidence to collect

- Commands or deterministic checks that were run.
- Changed files or generated artifacts.
- Screenshots or rendered QA only when a visual surface changed.
- Known residual risks and skipped checks.

## Related routes

- build_brief: https://newruntime.com/projects/coding-agent-cost-controls/build-brief.md
- project_json: https://newruntime.com/projects/coding-agent-cost-controls.json
- html: https://newruntime.com/projects/coding-agent-cost-controls/