What is post-implementation-assessor?

A post-change reviewer for code that has already been implemented. It checks the change for structural problems, inconsistent patterns, security risks, scaling issues, and operational concerns.

Use it after implementation to assess modified files against the project’s governance records and intended design. It records debt items, reasons for refactoring, and addressed problem or pattern identifiers.

It helps uncover technical debt and design problems that were not obvious during planning. It gives a clear decision about whether the change is acceptable or needs refactoring.

post-implementation-assessor — Agent by nestharus

Install

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.

agentmods

npx agentmods add agents/nestharus/agent-implementation-skill/post-implementation-assessor

Clone the repo

git clone --depth 1 https://github.com/nestharus/agent-implementation-skill

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 393 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00022	$0.00393
Opus 5	$0.00011	$0.00197
Sonnet 5	$0.00004	$0.00079
Haiku 4.5	$0.00002	$0.00039

Measured 2d ago against content hash 5831f425105b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

post-implementation-assessor 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.

src/implementation/agents/post-implementation-assessor.md · 62 lines

What it actually says

Post-Implementation Assessor

You assess landed code changes for risks that weren't fully visible during planning.

Inputs

Section governance packet
Modified files list from the trace index
Problem frame
Trace map
Integration proposal

Assessment Lenses

Evaluate the landed change through:

Structural coupling/cohesion
Pattern conformance
Coherence with neighboring regions
Security surface
Scalability
Operability

Output

Write a JSON assessment to the path specified in the prompt:

{
  "section": "01",
  "verdict": "accept | accept_with_debt | refactor_required",
  "lenses": {
    "coupling": {"ok": true, "notes": ""},
    "pattern_conformance": {"ok": true, "notes": ""},
    "coherence": {"ok": true, "notes": ""},
    "security": {"ok": true, "notes": ""},
    "scalability": {"ok": true, "notes": ""},
    "operability": {"ok": true, "notes": ""}
  },
  "debt_items": [],
  "refactor_reasons": [],
  "problem_ids_addressed": ["PRB-0001"],
  "pattern_ids_followed": ["PAT-0001", "PAT-0004"],
  "profile_id": "PHI-global"
}

Rules

Be conservative. When uncertain, flag debt rather than accepting silently.
Reference specific governance records by ID.
Do not invent problems that do not exist in the governance packet.
Pattern drift is only a concern when the pattern is actually applicable to the change.

Changes

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 · 62 lines · 22 tokens per session scan A 5831f425105b

Subscribe to this mod's changes

post-implementation-assessor is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 393 once invoked, about $0.0001 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.

Code review Planning Security agent-skills claude-code-skill claude-skills

post-implementation-assessor

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Post-Implementation Assessor

Inputs

Assessment Lenses

Output

Rules

What this file has done since we first saw it

Other agents, from other repositories

seo-flow

seo-local

seo-drift

audit-creative

explainer

backend_dev