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 skills add Tx1207/hello-scholar --skill converge-to-specgit clone --depth 1 https://github.com/Tx1207/hello-scholarWrote 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/tx1207/hello-scholar/converge-to-spec)<a href="https://agentmods.dev/skills/tx1207/hello-scholar/converge-to-spec"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/converge-to-spec/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/tx1207/hello-scholar/converge-to-spec"><img src="https://agentmods.dev/badge/skills/tx1207/hello-scholar/converge-to-spec.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 | $0.00028 | $0.00386 |
| Opus 5 | $0.00014 | $0.00193 |
| Sonnet 5 | $0.00006 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
converge-to-spec 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.
What it actually says
Converge to Spec
Compare the real implementation with the selected Spec, including a draft or partially implemented Spec. An audit is read-only regardless of progress; if the user asks to audit and fix, identify the gaps, then continue with in-scope repairs and verification under the same authorization.
Establish the comparison
Identify the exact Spec path, revision, status, target code or worktree state, and initial Git changes. Read the Spec, relevant Architecture, code, tests, configuration, and linked experiment Records. Use historical Plan/Tasks only when explicitly auditing an unmigrated legacy bundle, and state that boundary; they do not control current execution.
Run hello-scholar docs check when available. A draft status, partial implementation, or failing check is evidence to report, not a reason to refuse the comparison.
Audit acceptance
For every material AC-NN, record:
- the requirement and current conclusion: satisfied, partial, missing, contradictory, or not verifiable;
- severity and user impact;
- direct evidence with paths, lines, commands, results, or a linked Record;
- the smallest credible repair or verification direction.
Also identify unrequested interfaces, dependencies, compatibility layers, duplicate owners, or stale behavior within the Spec's boundary. Tests passing do not prove an AC they do not cover, and old summaries do not replace current evidence. Do not invent logs when no executable verification exists; use code evidence and state its limit.
Return the result
Lead with material findings, then summarize satisfied acceptance and the exact fresh commands still needed. Name the compared Spec revision and working-tree state so the result can be interpreted later. Do not modify source, tests, Specs, Records, Architecture, or Indexes during the audit.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -53 lines · -19 tokens per session 9cc1e691c19b
- 11d ago First seen · 83 lines · 47 tokens per session scan A c1e455b5dd27
converge-to-spec is a skill published in the GitHub repository Tx1207/hello-scholar (6 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 386 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…