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 jovesun-lab/arcgram --skill reconcilegit clone --depth 1 https://github.com/jovesun-lab/arcgramWrote 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/jovesun-lab/arcgram/reconcile)<a href="https://agentmods.dev/skills/jovesun-lab/arcgram/reconcile"><img src="https://agentmods.dev/badge/skills/jovesun-lab/arcgram/reconcile.svg" alt="Measured on agentmods" 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 | $0.00115 | $0.00945 |
| Opus 5 | $0.00057 | $0.00473 |
| Sonnet 5 | $0.00023 | $0.00189 |
| Haiku 4.5 | $0.00012 | $0.00094 |
Grade A, and why
reconcile 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconcile - code<->diagram @spec bijection validator
Two inputs: a diagram + the code it describes.
One question: do the diagram's @spec values still equal the same-named code constants?
Returns typed findings; marks, never blocks.
Sibling to Checkpoint: Checkpoint checks structure from the diagram alone; Reconcile checks values across diagram + code. Run both -> the diagram is a faithful, current spec.
Input: the @spec line
A node pins values on one line at the top of desc:
@spec hold_ms=800 fade_ms=200 <- Reconcile reads ONLY this line
- Prefix
@spec(ASCII).key=value, key = the code constant name. - Match is case/separator-insensitive:
hold_ms=HOLD_MS=holdMs=hold-ms. - Value: a number (
800,0x320) or a quoted string ("left"). - Free prose and a
~ tune: <range>line are for humans - never read.
Reconcile reads only the @spec line + named code constants. No geometry, no prose,
no program behavior.
Findings
| finding | severity | means |
|---|---|---|
spec-drift |
defect | @spec value != the code constant |
spec-no-constant |
defect | no same-named constant in the code |
malformed-spec |
defect | @spec line is not key=value |
value-uncovered |
uncovered | constant is computed, not a literal - no verdict |
ambiguous-constant |
uncovered | two constants normalize to one name |
no-spec-lines |
uncovered | nothing pinned - never a false "clean" |
Anchored on the @spec line (not the code): drift is caught both ways, but a code constant
on no @spec line is normal, not a finding. The extractor is a tolerant, dependency-free scan of
const/let/var =, NAME =, NAME:, #define, :=, [modifiers] const|readonly TYPE NAME =, and
C#/Unity bare field initializers [attr] public|private|static TYPE NAME = value (ScriptableObject
tuning fields, no const/readonly) (JS/TS/Python/C/Go/C#/Java); numbers normalize (800 == 800.0 ==
0x320, and a C#/Java numeric suffix is dropped so 0.2f == 0.2, 800L == 800). A Unity bare
field is matched only with a field-only marker (an access modifier, [Attribute], or static), so a
method-body local (int x = 5;) is never captured.
What ships with it
3 files 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.
- 8d ago First seen · 80 lines · 115 tokens per session scan A b69c4513df6d
reconcile is a skill published in the GitHub repository jovesun-lab/arcgram (9 stars, last pushed 20d ago), licensed Apache-2.0. It adds 115 tokens to every session and 945 once invoked, about $0.0006 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
troubleshooting
Common ComfyUI errors and fixes. OOM, missing nodes, dtype mismatches, black images, and debugging strategies.
operating-cadence
Designs the rhythm an organization runs on — which reviews happen weekly, monthly and quarterly, what each one decides, who owns the numbers presented, and how a signal at the front line reaches the people who can act on it. Use this to set up a management operating system, fix a meeting calendar that produces no…
debug-render
Debug a WRONG or imperfect render (not a hard error) by inspecting inputs and intermediate steps with run-to-node. Render one branch up to an output, preview-tap latents/masks/preprocessor maps, localize the first bad stage, then fix. Use when a final image/video completes but looks wrong, such as artifacts, wrong…
ci-debug
Diagnose a failing CI run against an 11-pattern playbook. Classifies the failure, cites the relevant memory entry, proposes the exact fix command — but NEVER applies without explicit user approval. Use when a specific PR check or GitHub Actions run failed and you want a diagnosis instead of speculation. Don't use for…
paired-probe
Refuse a verdict a probe did not earn. Runs a check where the fault IS present and where it is NOT, and blocks the answer when both arms print the same thing, because a check that cannot disagree with you has measured nothing. Also catches the zero-sample sweep that reads as "clean" and the swallowed error that reads…
report-bug
Self-heal and report bugs. Use when a defect in comfyui-mcp, the sidebar panel, a third-party custom node, or ComfyUI core actually cost the user something - it blocked them, produced a wrong result they would keep, lost or corrupted work, or crashed ComfyUI. For OUR repos (comfyui-mcp, comfyui-mcp-panel…