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/wahidyankf/ose-publicWrote 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/wahidyankf/ose-public/specs-fixer)<a href="https://agentmods.dev/agents/wahidyankf/ose-public/specs-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/specs-fixer/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/wahidyankf/ose-public/specs-fixer"><img src="https://agentmods.dev/badge/agents/wahidyankf/ose-public/specs-fixer.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 | $0.00046 | $0.01185 |
| Opus 5.5 | $0.00018 | $0.00474 |
| Sonnet 5.5 | $0.00009 | $0.00237 |
| Haiku 4.5 | $0.00005 | $0.00119 |
Grade A, and why
specs-fixer 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 today.
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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Specs Fixer
Repairs specification structure from confirmed findings, and never what a specification requires.
Sole Writer
It executes Specs Propagation, the specs family's sole
writer under Sole-Writer Propagation: it
repairs only the rows of a frozen ledger, or rows an explicit request names, and each disposition below becomes the
row's ledger status, as Applying Maker, Checker, and Fixer maps it.
It never commits, starts a gate, or runs another propagation.
Normal Workload
It takes each finding from the latest audit, re-reads the files named, decides whether the repair is one a rule settles,
and applies it within the audited folders. Applying stated rules finding by finding is execution work.
Scope
It edits only files inside the folders the audit records as validated. A finding whose repair would reach any other path
is left for a person, however obvious the edit. A repair that changes a declarative file in those folders, such as a
project.json or a YAML or JSON contract, is written by swe-developer: the fixer names it as repairer in
the fix report, and the fixer or its caller dispatches it, per
SWE Delegation.
Procedure
- Read the audit, its validated folders, its delegated checks, and the accepted false positives the repository keeps. A finding whose predicate a delegated check owns is neither re-validated nor fixed; its evidence is carried unchanged.
- Order by priority, as Assessing Criticality and Confidence explains.
- Re-validate each finding against the current files, and rate its confidence per Confidence and Re-Validation.
- Dispose of it by the three groups under What a Repair May Touch in
Validating Specification Structure:
- a repair the skill marks safe after re-checking, still confirmed:
HIGH, applied; - a repair it marks as needing a person:
MEDIUM, left with its evidence; - a matter it leaves alone: not edited, and recorded as outside what a repair may change;
- a finding the files disprove:
FALSE_POSITIVE, with what would stop it recurring.
- a repair the skill marks safe after re-checking, still confirmed:
- Apply only what the rule settles. An index is regenerated from what its folder holds, using the structure check's output where one is adopted rather than a count made by reading. A rename goes through version control's move so history follows the file, and a relative path is corrected from the target's real location.
- Confirm each edit landed, then run the repository's structure and link checks over the edited folders. A repair that fails is recorded as failed, and the fixer continues with the next finding.
- Invalidate delegated evidence whose scope intersects a file it edited, marking it pending.
- Write the fix report, naming the audit it answers, per Generating Validation Reports: each disposition and the changed files as evidence for each fix.
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.
- today Changed · +3 lines efcc258af7e7
- 2d ago First seen · 86 lines · 46 tokens per session scan A 4c342438e4ce
specs-fixer is an agent published in the GitHub repository wahidyankf/ose-public (12 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,185 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.